Skip to main content
Glama

GetEverwear second-hand clothing catalogue

Chercher des pièces

chercher_pieces
Read-onlyIdempotent

Cherche dans le catalogue GetEverwear (vêtements et accessoires de seconde main, pièces uniques) les pièces EN VENTE. Le texte peut être une phrase (« robe femme taille 38 moins de 40 euros », « blue shirt ») : la taille, la pointure, le budget, l'état, « pas cher », « nouveautés » et homme/femme y sont reconnus. Filtres facultatifs : rayon (handle donné par lister_rayons), taille (ex. M, 38, W32), marque, prix minimum et maximum en euros, état minimum, tri, limite. Rend au plus 20 pièces : titre, prix, taille, état, couleur, une photo et le lien de la fiche ; « approximatif » vaut true quand aucune pièce ne porte tous les mots et que les plus proches sont rendues.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "chercher_pieces"
  }
}

Input Schema

NameRequiredDescriptionDefault
triNoOrdre des pièces (pertinence par défaut).
rayonNoHandle d'un rayon renvoyé par lister_rayons (sous-rayons compris).
texteNoRecherche en texte libre ou en phrase (français de préférence ; types et couleurs courants compris en anglais, espagnol, allemand, italien, portugais, néerlandais).
limiteNoNombre de pièces à rendre, ramené entre 1 et 20 (20 par défaut).
marqueNoNom de la marque, ex. Ralph Lauren.
tailleNoTaille exacte, sans casse : M, 38, W32...
etat_minNoÉtat minimum de la pièce.
prix_maxNoPrix maximum en euros.
prix_minNoPrix minimum en euros.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world semantics, so the safety profile is covered. Beyond that the description discloses real behavior: a hard cap of 20 results, the exact returned fields, and the meaning of the 'approximatif' flag when no piece matches every word. Pagination handling beyond the limit cap is the only notable omission.

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?

Front-loads purpose, then query capabilities, then optional filters, then return shape — a logical progression with no filler sentences. It is dense but slightly redundant in re-enumerating filters that the schema already documents in full.

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?

With no output schema, the description carries the return-value burden and does so well (fields, 20-item cap, approximate flag). All nine parameters are addressed and the key prerequisite is stated; only edge behavior such as empty-result handling is left implicit.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: that size, shoe size, budget, condition, 'pas cher', 'nouveautés' and gender can all be encoded inside the free-text query. It also restates the filter set with example formats (M, 38, W32) and specifies sort/limit semantics via the returned cap.

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?

States a specific verb (cherche) and resource (pièces in the GetEverwear catalogue) and narrows the scope to items EN VENTE, distinguishing it from a detail lookup like fiche_piece. It also names the sibling lister_rayons as the source of valid rayon handles, so an agent can tell the search tool apart from catalogue-navigation tools.

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?

Gives clear context for use (finding on-sale pieces, with natural-language queries) and names the prerequisite for the rayon filter (handle from lister_rayons). It does not explicitly say when to prefer fiche_piece or when not to use this tool, but the retrieval purpose is unambiguous.

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