Skip to main content
Glama
Sign In
mcp-pilotage

mcp-pilotage

by fmenguy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

trouver_fichiers

Locate files by name or path across all projects using glob patterns to answer where specific files such as CLAUDE.md, Dockerfile, or novel chapters live; heavy build and dependency folders are ignored.

Instructions

Cherche des fichiers par leur NOM ou leur chemin à travers tous les projets, via un motif glob. Complémentaire de chercher_partout qui fouille le contenu : ici tu réponds à des questions de localisation, par exemple où sont tous les CLAUDE.md, quels projets ont un fichier .mcp.json, où vivent les chapitres du roman, quels dépôts contiennent un Dockerfile. Les dossiers lourds (node_modules, dist, build, .astro, venv, pycache, .git) sont toujours ignorés.

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": {
      "motif": "<motif>"
    },
    "name": "trouver_fichiers"
  }
}

Input Schema

NameRequiredDescriptionDefault
motifYesMotif glob appliqué au chemin relatif dans chaque projet. Exemples : « CLAUDE.md », « **/*.astro », « src/**/*.py », « **/Dockerfile ». Le « * » couvre un segment, le « ** » plusieurs.
projetsNoNoms ou chemins des projets à explorer. Si absent, tous les projets de l'inventaire sont explorés.
profondeurNoProfondeur maximale de descente dans l'arborescence de chaque projet.
max_resultatsNoNombre total de fichiers renvoyés au maximum.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and it delivers a key behavioral trait: heavy directories (node_modules, dist, build, .astro, venv, __pycache__, .git) are always ignored, which an agent could not otherwise know. It omits how results are returned or ordered, but for a read-style search tool the ignore rule is the most important disclosure.

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?

Purpose is front-loaded in the first clause, the sibling differentiation follows, and the example questions and ignore-list are compact and additive. Every sentence contributes information not present in the schema or annotations.

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 four-parameter search tool with no output schema, the definition covers purpose, alternative, typical questions and the directory-ignore rule. The only real gap is the shape of the returned results (grouping by project, ordering, path format), which an agent would need to interpret output correctly.

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 the schema already documents motif, projets, profondeur and max_resultats with examples and defaults. The description adds no parameter-level detail beyond the schema, so baseline 3 applies.

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 and resource ('Cherche des fichiers par leur NOM ou leur chemin') plus the mechanism ('via un motif glob'), and explicitly distinguishes itself from the sibling chercher_partout by naming what that tool does instead (content search). No ambiguity about which tool to pick.

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

Usage Guidelines5/5

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

Gives an explicit when-to-use rule ('questions de localisation') and names the alternative (chercher_partout) with the condition that selects it (content search vs. name/path search). The four concrete example questions make the intended use cases tangible.

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

Deploy Server

Other Tools