Skip to main content
Glama

Motif & Moi

Préparer le vêtement et son lien de commande

create_design

Enregistre la personnalisation (logo par URL https publique ou en base64, textes, prénoms et numéros par pièce, quantités) et renvoie un lien vers le configurateur prérempli, un aperçu et le devis. Rien n’est commandé : le client ouvre le lien, vérifie le visuel (bon à tirer), puis commande et paie lui-même. Le lien reste valable 90 jours.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "category": "<category>"
    },
    "name": "create_design"
  }
}

Input Schema

NameRequiredDescriptionDefault
colorNoCouleur du vêtement (nom de list_products, ex. Noir).
sizesNoQuantités par taille, ex. {"M": 10, "L": 5}. Inutile avec pieces.
textsNoTextes imprimés. Pour un prénom ou un numéro différent sur chaque pièce : per_piece, sans text, et la liste pieces.
piecesNoUne entrée par pièce quand un texte est « par pièce » : taille, prénom, numéro.
qualityNoQualité : eco, standard (défaut) ou premium, selon la catégorie.
categoryYesCatégorie (identifiant de list_products), ex. t-shirt, sweat, hoodie, polo, tote-bag.
logo_urlNoAdresse https publique du logo (PNG, JPG, WebP ou SVG, 10 Mo max).
shippingNo
logo_sizeNoTaille dans la zone : s (petit), m (moyen, défaut), l (grand).
logo_sidesNoFaces qui portent le logo (défaut : front).
logo_base64NoLogo encodé en base64 (à la place de logo_url).
postal_codeNoCode postal français de livraison : donne la date de réception.
front_formatNoDevant : petit logo sur le cœur (compris dans le prix) ou grand format (supplément).
logo_filenameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / logo_url / description
      Previous value: -"Adresse https publique du logo (PNG, JPG, WebP ou SVG, 20 Mo max)."New value: +"Adresse https publique du logo (PNG, JPG, WebP ou SVG, 10 Mo max)."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare non-readOnly, non-idempotent, non-destructive and open-world; the description adds substantive context on top: nothing is ordered, the client must visually validate (bon à tirer) before paying, and the generated link lives 90 days. It does not say what happens if the tool is called twice (non-idempotent) or how validation failures surface, which keeps it from a 5.

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

Conciseness5/5

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

Three tightly written sentences: what is saved, what is returned, and what the caller must understand about the non-ordering contract and link lifetime. Front-loaded and free of filler.

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

Completeness4/5

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

For a 14-parameter mutation tool with nested objects and no output schema, the description compensates well by naming the three return values and the core behavioral contract. It leaves gaps on repeat-call behavior and on how it relates to get_quote/get_design_preview, which an agent working with 6 siblings would benefit from knowing.

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

Parameters3/5

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

Schema coverage is 86%, so the schema already documents nearly every parameter in detail, including enums, defaults and formats. The description restates the categories of input (logo URL/base64, texts, per-piece names/numbers, quantities) but adds no format or constraint details beyond what the schema provides. Baseline 3 applies when the schema does the heavy lifting.

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

Purpose4/5

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

The description gives a specific verb and resource ('Enregistre la personnalisation') and enumerates the payload (logo via URL or base64, texts, per-piece names/numbers, quantities). It also states the outputs: a pre-filled configurator link, a preview and the quote. It stops short of naming the sibling it differs from (create_group_order), so sibling differentiation is implicit rather than explicit.

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

Usage Guidelines3/5

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

'Rien n'est commandé' implies this is a preparation step before the client orders, which gives some usage context. However, there is no explicit guidance on when to use this versus create_group_order, or when to follow with get_design_preview or get_quote. The agent must infer the sequencing from sibling names.

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.

Resources