Capucine

Je cherche dans les fiches cuir

chercher_fiches

Read-onlyIdempotent

Je filtre les fiches de jupes et pantalons en cuir de mes comparatifs : animal, doublure, coupe, couleur, longueur ou entrejambe en cm, prix, marque. Chaque fait est déclaré par le vendeur et sourcé ; une fiche muette sur un critère est écartée et comptée « non renseignée », jamais devinée. Aucun essai physique.

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_fiches"
  }
}

Input Schema

Name	Required	Description	Default
`tri`	No	prix = du moins cher ; completude = fiches les plus renseignées d'abord.	prix
`coupe`	No	Coupe déclarée, ex. crayon, trapèze, droit, évasé, slim, portefeuille.
`limit`	No	Nombre de fiches renvoyées, 1 à 20.
`piece`	No	jupe ou pantalon (en cuir). Vide = les deux.
`animal`	No	Animal déclaré, ex. agneau, chèvre, veau, porc, mouton. Vide = sans filtre.
`marque`	No	Marque, ex. Sézane, IKKS. Vide = toutes.
`couleur`	No	Famille de couleur, ex. noir, bordeaux, chocolat, camel, beige.
`doublure`	No	Matière de doublure (ex. viscose, polyester), « oui » ou « sans ». Vide = sans filtre.
`prix_max`	No	Prix observé maximum en euros.
`entretien`	No	Mot de la consigne d'entretien, ex. spécialiste, nettoyage à sec.
`detail_level`	No	brief = faits clés ; full = tous les faits déclarés, disponibilité et sources.	brief
`longueur_max_cm`	No	Longueur de jupe ou entrejambe maximale annoncée, en cm.
`longueur_min_cm`	No	Longueur de jupe ou entrejambe minimale annoncée, en cm.
`inclure_effet_cuir`	No	true pour inclure les pantalons « effet cuir » (enduit, PU) du comparatif.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, but the description adds real behavioral content: every fact is seller-declared and sourced, records silent on a filtered criterion are excluded and counted as "non renseignée" rather than guessed, and no physical testing backs the data. That silently-dropped-records rule is material for interpreting results and is not derivable from the schema or annotations.

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?

Three front-loaded sentences, roughly 55 words, with the resource and its filterable attributes stated first. Every sentence carries weight; "Aucun essai physique" is a borderline disclaimer but does clarify data provenance.

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 read tool with full schema coverage, an output schema, and rich annotations, the description covers dataset scope, filterable dimensions, provenance, and the missing-data exclusion rule. The main gap is the absence of routing guidance relative to overlapping siblings such as comparer_pieces or shopping_search.

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 description coverage is 100%, so every parameter (tri, coupe, limit, detail_level, inclure_effet_cuir, etc.) is already documented in the input schema. The description restates the filterable fields (animal, doublure, coupe, couleur, longueur/entrejambe, prix, marque) but adds little syntax or semantics beyond them, apart from the exclusion rule that governs all filter params. Baseline 3 is appropriate.

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?

"Je filtre les fiches de jupes et pantalons en cuir de mes comparatifs" gives a specific verb (filtre) plus a bounded resource (curated leather skirt/pants comparison records) and enumerates the filterable attributes. The scope is unmistakable, but it never distinguishes this tool from siblings like comparer_pieces or get_piece_hub.

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?

Usage is implied rather than stated: the records come from "mes comparatifs" and only leather pieces are covered, so an agent can infer the tool is for narrowing within the curated catalogue. There is no explicit when-to-use versus when-to-use-something-else guidance, and no sibling is named as an alternative.

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

All Capucine tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?