ApparelHub

Accept a pending invite by token. The authenticated key-holder’s email must match the invite. Works on any tier and with a workspace-scoped key (the invitee side). Returns the account + workspace you were added to. [#e7e5ee]

Activate a store so it can list products and ingest orders. Requires at least one fulfillment provider (e.g. Printful) to be connected first — otherwise this fails. Use after create_store or unarchive_store once a provider is connected. [#87c31f]

Add an item (e.g. another variant of the same product) to a DRAFT order, before it is confirmed to production. Optionally set custom_price (the new item's per-unit retail price) and/or shipping_cost (the order-level retail shipping the customer pays — NOT the provider's cost); omit them and the variant price / existing shipping are kept. Only works while the order is in "draft" status. Printful and Gelato edit the existing provider draft IN PLACE; Printify has no edit API, so it CANCELS + RE-CREATES the order — the result then carries edit_method="recreated" and a new fulfillment_external_id. Nothing is charged on a draft, so re-creation is safe. Returns 409 "order_not_editable" if the order was already confirmed/submitted to production. [#f416d1]

Add one or more products (by uuid) to a collection. The products must already be associated with the store. If the collection is synced to a channel, the products are added there too. [#e8080a]

Add variants to an existing product (split primitive). Resolves provider_variant_ids by color+size from the product's provider options (or pass them explicitly). Warns on the AQUA-vs-Navy trap. Variants must exist before syncing. [#c9cff4]

Aggregate KPIs broken down by one dimension: product_type, sales_channel, fulfillment_provider, product, variant, or hold_reason. Rows are sorted for display; overflow past the limit folds into an "(everything else)" row so totals still reconcile. Requires an Advanced Analytics plan. Read-only. [#127113]

Operational health for a date range: fulfillment velocity (payment→submit→ship→deliver averages), order counts, and cancellation / refund / hold rates, plus a hold-reason breakdown. Requires an Advanced Analytics plan. Read-only. [#ed8ddd]

Cross-client portfolio: per-workspace (per-client) KPIs plus rolled-up totals — the agency view. Groups store rollups by each store's current workspace over every workspace you can view analytics in. Requires an agency (Enterprise) account with Advanced Analytics; other accounts get a feature_unavailable error. Read-only. [#65a008]

Headline order/merch KPIs for a date range (gross revenue, orders, units, AOV, COGS, gross profit, margin, cancel/refund/hold rates, fulfillment velocity) plus prior-period deltas. Defaults to the last 30 days. Requires an Advanced Analytics plan (Professional or Enterprise). Read-only. [#6b72a2]

KPI trend series over a date range, bucketed by day, week, or month (zero-filled). Each bucket carries gross revenue, gross profit, COGS, order count, units, AOV, average margin, and margin coverage. Requires an Advanced Analytics plan. Read-only. [#48246d]

Surface insights from the merchant's own products + orders: best sellers, top channel, average order value. Read-only. Own-account signal (cross-merchant intelligence is a future feature). [#f6f4f3]

Escape hatch: make an authenticated request to any ApparelHub agent API endpoint under /agents/v1, as the connected account. PREFER a dedicated tool when one exists (they return clean, guarded results) — use this only for capabilities no tool covers. Call get_api_reference first to find the right path. `path` is relative (e.g. "orders", "store/<uuid>/settings"); no full URLs. Scoped to the account's own permissions. [#48e53d]

Approve an order that is awaiting approval, releasing it for fulfillment. For sales-channel (webhook) orders this also auto-submits the order to the fulfillment provider (Printful/Printify). Use when an order is held for review and the user wants to let it proceed. [#9b6ea5]

Approve a design-approval hold on an order so the provider can proceed. If the provider can't flip the hold via its API (Printful today), the result is deferred with a dashboard_url to finish the approval manually — the hold stays active until the provider's release fires. Get the hold_uuid from list_order_holds. [#7b5295]

Archive a design so it stops showing in the default gallery listing. Reversible with restore_design, and safe: it never touches products that already use the design. This is the right way to retire an unwanted or orphan design. Prefer it over delete_design unless the design must be removed permanently. Find orphan designs first with list_my_designs(on_products=false). [#16a475]

Archive a product: unsync it from every connected sales channel and its fulfillment provider, then hide it. Fails (returns blocking_orders) if any pending order still references its variants — cancel or fulfill those first. Restore it later with restore_product. Use archive rather than delete_product when a product has order history. [#4b1462]

Archive a store (use instead of delete for stores with order history — order records are kept for accounting, but the store is hidden from the default listing and stops ingesting new orders). Restore it later with unarchive_store. Set disconnect_provider=true to also disconnect every connected fulfillment provider and remove its stored credentials. [#b85c96]

Assign an account member to a workspace with a role, or update their existing role (agency / Enterprise). The target must already be a member of the account (invite_member first). Needs an account-wide key. [#5ec6df]

Propose (and, with dry_run=false, apply) optimizations across listings. Uses the sales channel's own demand data, so a listing that people SEE but do not buy is flagged for a listing fix rather than archived — that listing is proven demand with broken conversion, and archiving it destroys the best opportunity in the catalogue. Only a listing the channel reports as genuinely inert is ever archived. Where no demand data is available the proposal is "review" and NOTHING is applied. DEFAULTS TO DRY-RUN; applying only ever archives (never deletes, never goes live). [#170c11]

Browse ONE fulfillment provider's catalog for garments to print on. `category` is resolved against THAT provider's own taxonomy (providers use different vocabularies for the same idea) and an unknown category is rejected with the valid list rather than quietly returning everything. `keyword` matches product names across the whole catalog. ALWAYS read `warnings` in the response: they tell you when your results are narrower than you asked for -- e.g. a category that only exists inside one department. Each garment carries `decoration_method` / `accepts_photoreal` (`accepts_photoreal` absent means the provider publishes no signal -- unchecked, NOT unsuitable). This searches a SINGLE provider: to ask what the whole account can do, or before concluding a garment cannot take a design, use find_garments. Read-only. [#5e449d]

Cancel an order. Cancels it locally and, where possible, cancels the draft/order at the fulfillment provider (Printful/Printify). This does NOT refund the customer on the sales channel — the channel is the source of payment. Destructive: only cancel when the user explicitly asks. [#9e800b]

Change a product price once and propagate it: the platform cascades to all variants, and (when store_uuid is given) this re-syncs each connected channel so the price is consistent everywhere. Avoids the "changed on one channel, forgot the others" footgun. [#b8aca8]

Which of your connected sales channels report performance data, and which metrics each one supplies. Check this before concluding a listing has no traffic: a channel that reports nothing looks identical to a channel reporting zeros unless you look here. Also flags shops that must be RECONNECTED before performance data can flow. Read-only. [#df2820]

The listings wasting the most demand: proven traffic, broken conversion, ranked by how many people saw them and did not buy. This is the natural starting point for an optimisation pass — fix these before touching anything else, because the demand is already there and only the listing is in the way. Also returns per-state counts and, separately, the listings that are genuinely inert (state "dead") and therefore safe to archive. Nothing else is safe to archive. READ `shop` BEFORE acting on anything else here. If the shop as a whole is getting almost no views, safe_to_archive will be empty and top_opportunities will be thin — not because the listings are fine, but because nothing has been seen enough to judge. That is a distribution problem and no listing edit will move it. Read-only. [#7c8c30]

What the sales channel reports about each of your listings: impressions, clicks, click-through rate and units sold, plus a state telling you what to do about it. Use this to find listings people SEE but do not BUY — the order-based analytics tools cannot show you those, because to them a listing with 5,000 views and no sales looks identical to one nobody has ever seen. States: winner (scale it), conversion_blocked (lots of views, few clicks — the listing card is losing them), pdp_blocked (they click but do not buy — the product page is losing them), starved (too few views to judge; needs discovery, NOT a rewrite), dead (no activity at all; the only state safe to archive), no_channel_data (synced to the channel, but the channel has never reported it — usually means it is not actually live; check the listing before anything else), insufficient_data (not enough signal, or this channel does not report it). READ `summary.shop` FIRST. If it says no_channel_traffic, the whole shop is barely being served and no per-listing state means anything yet — the problem is distribution, and editing titles or images cannot fix a listing nobody is shown. Each row says which channel and store it came from — always check that before comparing two rows, since a channel product id is only unique within its own channel. ALWAYS check the coverage block before treating a missing metric as zero. Read-only. [#73dd2d]

Poll whether a dispatched connection has completed. Call this repeatedly after start_channel_connect while the user authorizes in their browser, and announce the result when it lands: they cannot see this conversation from the tab they authorized in, so if you do not tell them, nobody does. Read-only, makes no provider call, and is safe to poll every few seconds. connected true means say so and continue setup. connected false means keep waiting. needs_reconnect means retrying will never work and you must dispatch a fresh link with start_channel_connect. [#807361]

Advisory pre-flight for IP / trademark / prohibited-content risk. Scans the prompt/name and any detected text against common protected marks. NOT legal advice, and NOT an image-content trademark check. [#fba5cb]

Dry run: report whether a generated design can be MOVED to another workspace, without changing anything. Returns {eligible, blockers} — a non-empty blockers list (a product using the design is in use, or forbidden_source/destination) means move would fail, so copy instead. Read-only. [#1e988c]

Fetch one fulfillment issue in full (affected items, evidence attachments, provider claim tracking, resolution) and, by default, the provider-ready problem report: a copy-paste summary_text plus the provider dashboard deep-link where the report must be filed (Printful/Printify accept problem reports only in their own dashboards). Read-only. [#2f6bdb]

Poll the fulfillment provider for the latest status of an order and update it locally (including any design-approval holds). Read-mostly refresh — safe to call repeatedly. Use to see whether an order has shipped or is on hold at the provider. [#81b1a2]

Dry run: report whether a product can be MOVED to another workspace, without changing anything. Returns {eligible, blockers} — a non-empty blockers list (e.g. asset_in_use, asset_has_orders, forbidden_source/destination) means move would fail, so copy instead. Read-only. [#81f916]

What this account already has, what it still needs, and the single next action to take. Returns ready_to_design / ready_to_fulfill / ready_to_sell, a per-store breakdown, and an ordered next_steps list. Start here for any first-time setup, and call it again after each connection to confirm the state actually changed. Read-only, makes no provider calls, and is safe to poll. [#01f20c]

Dry run: preview deleting a workspace (agency / Enterprise) — the stores that would move to the Default workspace and the members whose assignment would be revoked. Changes nothing. Read-only. [#bcfd4e]

Confirm a DRAFT order to send it into production at the fulfillment provider. Only works for orders in "draft" status that have already been submitted to a provider (have a provider order id). Use after submit_order_to_fulfillment on a "prepare, then I confirm" store. [#ebe558]

Connect an API-token fulfillment provider (Printify, Gelato) to a store, entirely in chat. Validates the token first, so a bad token fails before anything is stored. If the token maps to more than one shop the result asks you to pick one and lists them — call again with shop_id set. For Printful use start_channel_connect instead: it needs a browser. Never repeat the token back to the user. [#98598c]

Connect an API-key sales channel (WooCommerce, Wix) to a store, entirely in chat. For Shopify and TikTok Shop use start_channel_connect instead: they need a browser. Credentials are write-only and are never returned. [#c9093d]

Copy a generated design image into another workspace (agency accounts). Non-destructive: the original stays put and the copy gets its own duplicated image file. Use list_my_workspaces for the destination uuid; pass source_workspace if the design is not in your Default workspace. [#3090dc]

Copy a product into another workspace (agency accounts). Non-destructive: the original is untouched and the copy lands as an unsynced DRAFT (no store mapping, fresh variants). Use list_my_workspaces to get the destination workspace uuid. If the product lives in a non-Default workspace, pass source_workspace too. [#d046a8]

Create a new (empty) collection in a store. Provide a name (sent to the platform as the collection title) and an optional description. Add products with add_products_to_collection, then sync_collection to push it to a sales channel. [#ff2c5e]

Create a STANDALONE product from a design (split primitive) — it is NOT placed on any store yet. Applies the correct field names + pricing floor, routes EMBROIDERY garments (caps/beanies) to their real embroidery placement with Printful thread colors (derived or explicit), and defaults face goods (canvas/backpacks/bags/socks/towels/blankets/pillows/cases...) to print_style "fill" (design recomposed onto a matching background, printed edge-to-edge). Set generate_mockup: true to render a garment mockup as the display image (it auto-derives representative variants from the catalog, so you do NOT need mockup_variant_ids) — otherwise the raw design is used as the display image. To get it onto a store and listed, the required sequence is: add_variants -> sync_to_fulfillment(product_uuid, store_uuid) [associates it with the store + syncs to Printful/Printify] -> sync_to_channel [sales channel]. To run that whole pipeline in one call instead, use ship_product. [#e8704a]

Create a new ApparelHub store. Only a name is required. The store starts CLOSED — connect a fulfillment provider (Printful/Printify), then call activate_store to make it ACTIVE. In an agency account pass workspace=<uuid> to create it in a specific client workspace. [#9d5cbc]

Create a new workspace in the account (agency / Enterprise). Name must be unique within the account. Needs an account-wide key; a tier without the agency feature gets feature_unavailable. Returns the new workspace uuid. [#51f6a7]

Delete a collection. If it is synced to any sales channel, the platform unsyncs it there first. The member products are NOT deleted, only the grouping. [#afdbfe]

Permanently delete a design and its stored files. Irreversible. Refused with design_in_use if any live product still uses the design, in which case archive_design is the safe alternative. Use archive_design unless the design genuinely must be erased. [#02e216]

Delete (default) or archive a product. Hard delete cascades to variants; if the product is synced to channels, unsync it first to avoid orphan listings — unsync_from_channel for one channel, archive_product for all of them. (sync_to_channel cannot unsync; it only syncs.) [#020483]

Delete a workspace (agency / Enterprise). Its stores are reassigned to the Default workspace and member assignments revoked first. The Default workspace cannot be deleted. Preview with check_workspace_deletion. Needs an account-wide key. [#c566a1]

Discover the channel-defined listing fields you can set — TikTok product attributes, eBay item specifics, WooCommerce product attributes — and what is currently set. READ-ONLY. Call this BEFORE set_listing_attributes or set_channel_settings: the field names and their allowed values are defined by the channel, so guessing them gets the value dropped. Pass `product_uuid` for one listing, or `integration_uuid` alone for the shop-wide settings (compliance answers, the shipping template, and a fallback size chart). BRAND and the per-listing SIZE CHART are per-PRODUCT, not shop-wide — both describe the blank, so a shop selling two blanks needs two values, and a shop-wide size chart would replace the accurate per-garment one on every other listing at once. Ask for them with `product_uuid`. Each field carries `value_type`, `cardinality` (single vs multi), `free_text` (whether a value outside the list is accepted) and `requirement`. Those are separate on purpose: most fields are enumerated AND accept free text, so neither flag alone tells you what is legal. `requirement: "conditional"` means the field only becomes required once `required_when` holds — typically after you answer a related question one particular way. `values` is what is LIVE ON THE CHANNEL, which is not the same as what was last written from here: platform auto-fills and merchant edits made directly in the channel's own admin show up here too. That drift is usually the most useful thing in the response. `unset_required` lists fields that are required and empty. Those are NOT filled in for you, deliberately — several are legal attestations. Left unset, the channel picks its own default or grades the listing down, so they are worth resolving with the merchant. ⚠️ CHECK `resolved_for.resolution` when it is present. `explicit_override` means the merchant chose the category. `keyword_match` means it was GUESSED from the product name, and a wrong guess means these fields belong to a different kind of product…

End-to-end apparel design with the platform lessons baked in: solid-green-background prompt, transparency keying, and (optionally) a local text check. Returns ready-to-use design(s). Streams progress. Set needs_transparency=false for all-over-print products. Rate-limit errors are classified (model_rate_limited = one model's provider vs platform_rate_limited = this key's ApparelHub throttle vs request_not_sent = the call never reached ApparelHub), and each design's fallback_trail shows any model substitutions. This GENERATES new artwork — when the merchant already owns the file (a logo, a brand mark, a cleared cover), use upload_design instead and do not regenerate their mark. [#d84efc]

Diagnose TikTok Shop listing quality and optionally apply TikTok's own recommendations. TikTok grades each listing POOR/FAIR/GOOD and a low grade suppresses reach. Returns, per listing: the current tier, the machine-readable issues behind it (code + how_to_solve + the tier that ONE fix unlocks), and TikTok's recommended search terms / titles / descriptions. READ-ONLY unless you pass `apply`. `apply:['search_terms']` is the safe default action — search terms are hidden listing metadata. Passing 'title' or 'description' replaces merchant-visible copy with machine-generated text, so ask the user first; those land on a TikTok-ONLY override and never rewrite the shared product record (which would also change the Shopify/WooCommerce/Wix listings). Use `dry_run` to preview. IMPORTANT — TikTok often flags a title WITHOUT offering a replacement, so `apply:["title"]` returns no_recommendation. That is not a dead end: each listing also carries `requirements` (the computed target, e.g. 40-150 chars — TikTok's own length rules contradict each other and this is the intersection), `building_blocks` (the product's real garment/colors/sizes, so you write from facts rather than inventing them), and `candidates.title` (ready-to-use options, shortest first, each already validated against the requirements). Offer the candidates to the user, or write your own title to the requirements and set it via update_product tiktok_listing.title. Check `issues[].fixable_by` before acting: `photography` means the listing needs new imagery, not better writing — report it rather than trying to write around it. ⚠️ `diagnosable` means "TikTok returned a diagnosis", NOT "this listing is live". TikTok also answers for deactivated and deleted listings, so a catalog can come back entirely diagnosable:true while a third of it is no longer for sale. Read `listing_health` for liveness: "Removed" is gone, "Needs Attention" is present but not visible to buyers, and null means we have never checked — which is NO…

Estimate production + shipping + tax + total for an order WITHOUT creating it (read-only against the fulfillment provider, no order placed). Give the store, the recipient, and the variants + quantities. Use to preview landed cost before placing an order. AVAILABLE FOR PRINTFUL AND GELATO ONLY: Printify offers no pre-order estimate, so a Printify-fulfilled store returns a refusal rather than a number — do not retry it, and do not present a cross-provider landed-cost comparison that silently omits Printify. Both country_code AND address1 are required; the platform rejects the request without a street address. The variants must already be synced to the fulfillment provider. [#a2bd48]