Skip to main content
Glama

Create an MU product

mu_create_product

Create a product in one of your MU stores. Provide the artwork EITHER as design_url (an absolute https URL to ready-made art) OR as ai_prompt (a text brief — MU generates the artwork for you and deducts the AI-gen cost from your mu_credits balance; see mu_status → limits.ai_gen for cost_jpy and whether it is enabled). Pass exactly one of the two. kind must be one of: tee, tee_white, rashguard_ls, rashguard_black, hoodie, crewneck, sticker, mug, tote, tank, cap, phone_case, long_sleeve_tee, shorts, beanie, leggings, joggers, apron, canvas, metal_print, pillow, blanket, coaster, placemat, journal, mug_black, wine_glass, towel, bottle, mouse_pad, laptop_sleeve, poster, nfc_coin, device, event_ticket, song, zine, video, karaoke_ticket, house, socks, drawstring_bag, beach_towel, fanny_pack, bucket_hat, kids_tee, backpack, flag, printful_custom. phone_case is an iPhone tough case (Printful) — the buyer picks their iPhone model (11〜17, all sizes) inside checkout, so you create ONE product and it ships to whichever model they choose. . Two digital kinds need an extra field: event_ticket (a sellable event ticket — pass capacity for the seat limit; on purchase the buyer is emailed a QR that opens a VALID ticket page; no shipping) and song (a sellable track — pass audio_url, the https link to the audio; on purchase the buyer is emailed a private listen/download link; no shipping). Other digital kinds (zine PDF, video, karaoke_ticket) and manual-fulfilment kinds (poster, tee_white, nfc_coin, device, house) all take the same design_url/ai_prompt artwork; the buyer gets a download/redemption link (digital) or the operator ships/builds it (manual). Products go live immediately for trusted owners unless the risk gate trips, otherwise they wait for MA-council review — ALWAYS report the status field from the response, do not assume. Requires Authorization: Bearer <api_key>.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindYesProduct kind. One of: tee, tee_white, rashguard_ls, rashguard_black, hoodie, crewneck, sticker, mug, tote, tank, cap, phone_case, long_sleeve_tee, shorts, beanie, leggings, joggers, apron, canvas, metal_print, pillow, blanket, coaster, placemat, journal, mug_black, wine_glass, towel, bottle, mouse_pad, laptop_sleeve, poster, nfc_coin, device, event_ticket, song, zine, video, karaoke_ticket, house, socks, drawstring_bag, beach_towel, fanny_pack, bucket_hat, kids_tee, backpack, flag, printful_custom.
labelYesProduct label / title.
storeYesSlug of the store to add the product to.
capacityNoevent_ticket only: seat limit (定員). Once sold out, checkout is blocked. Omit = unlimited.
positionNoOptional print placement — front-print DTG apparel only (tee / tee_white / hoodie / crewneck / tank / long_sleeve_tee). The preview mockup AND the real print order use the same resolved box (WYSIWYG). Preview with mu_preview_mockup before creating.
ai_promptNoText brief for MU to generate the artwork (<=600 chars). Costs mu_credits (see mu_status → limits.ai_gen). Provide this OR design_url (not both).
audio_urlNosong only: absolute https URL of the audio file delivered to the buyer on purchase.
price_jpyNoOptional retail price in JPY. Must respect the kind's price_floor_jpy (see mu_status).
design_urlNoAbsolute https URL to ready-made design artwork (ticket art / song cover for digital kinds). Provide this OR ai_prompt (not both).
descriptionYesProduct description.
printful_product_idNoprintful_custom only: the Printful catalog product id (from the Printful catalog API). MU makes ANY of Printful's ~500 catalog products this way — placement, fulfillment route and price floor are resolved live from Printful at create time.
printful_variant_idNoprintful_custom only: the Printful variant id (size/color) for the chosen product.

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so the description carries full burden. It discloses that products go live immediately for trusted owners unless the risk gate trips, requiring MA-council review. It also specifies the need for an Authorization header and the importance of checking the `status` field in the response.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is lengthy but every sentence adds value. It front-loads the main purpose and then systematically covers special cases and constraints. Could be slightly more concise, but it is well-structured and informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (12 parameters, nested objects, many product kinds), the description is thorough. It covers mandatory fields, artwork options, special handling for various kinds, the risk gate, authentication, and response handling. No output schema exists, but the description compensates adequately.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds significant meaning beyond the schema, e.g., explaining the mutual exclusivity of `design_url` and `ai_prompt`, detailing `phone_case` behavior, and providing special instructions for `event_ticket` and `song` kinds, as well as the `position` object usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create a product') and the resource ('in one of your MU stores'). It distinguishes this tool from siblings like mu_update_product and mu_retire_product by specifying creation context. The verb 'Create' and resource 'product' are explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use `design_url` vs `ai_prompt`, and explains special cases for `phone_case`, `event_ticket`, `song`, and other digital/manual-fulfillment kinds. It also mentions the risk gate and the need to report the `status` field. It does not explicitly list when not to use the tool, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose; no two tools appear to do the same thing. Even closely related tools (e.g., mu_quote vs mu_rfq_create, mu_preview_mockup vs mu_create_product) are differentiated by read-only vs. action, or draft vs. send.

Naming Consistency5/5

Tool names consistently use snake_case with the mu_ prefix, and follow a clear verb_noun or noun_verb pattern. Groups like mu_gi_*, mu_ship_*, mu_rfq_* maintain internal consistency. No arbitrary or ambiguous names.

Tool Count4/5

The tool count of 28 is on the higher side but appropriate for the breadth of functionality (registration, product lifecycle, manufacturing, shipping, sales, admin). It's well within a manageable range for a comprehensive server.

Completeness4/5

The tool surface covers core workflows comprehensively: registration, product CRUD (with create, update, retire), manufacturing quotes (informational and RFQ with spec drafting), shipping (CSV, tracking, status updates), sales data, and gi-specific management. Minor gaps include lack of store update/delete and product search, but these are not critical for the main use cases.

Resources