Skip to main content
Glama
Sign In
mcp-pilotage

mcp-pilotage

by fmenguy
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

decrire_projet

Retrieve a complete profile of a known project—path, remote, tech stack, dependencies, git status, commits, branches, context docs, and top-level tree—before reading its files or advising on it.

Instructions

Fiche complète d'UN projet : chemin, dépôt distant, pile technique et dépendances marquantes, rôle déduit, état git détaillé, derniers commits, branches, documents de contexte disponibles et arborescence de surface. Utilise cet outil quand tu sais déjà de quel projet tu parles et que tu veux tout savoir dessus d'un coup, avant d'aller lire ses fichiers ou de conseiller François sur ce projet. Pour lire vraiment le contenu de son CLAUDE.md ou de son README, enchaîne avec lire_cerveau.

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": {
      "projet": "<projet>"
    },
    "name": "decrire_projet"
  }
}

Input Schema

NameRequiredDescriptionDefault
projetYesNom du dossier du projet (par exemple « mon-api ») ou son chemin absolu. La correspondance est insensible à la casse et accepte un nom partiel s'il n'est pas ambigu.
nb_commitsNoNombre de commits récents à inclure dans la fiche.
inclure_arborescenceNoInclure la liste des dossiers et fichiers de premier niveau, pour situer l'organisation du projet.

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 load, and it does disclose that the role is inferred ("rôle déduit") and that the file tree is surface-level, which prevents over-reading the output. It never explicitly says the operation is read-only or what happens when the project name is ambiguous or absent, so the behavioral picture is strong on output shape but silent on failure modes.

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 sentences, each earning its place: the first enumerates return contents (necessary since there is no output schema), the second gives the selection rule, the third names the follow-up tool. The payload list is front-loaded and no wording is redundant.

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?

Because there is no output schema, the enumeration of the fiche's contents is essential and present, and all three parameters are documented elsewhere. The remaining gap is operational: nothing about cost, output size, or behavior when the project cannot be resolved, which matters for a broad aggregate read.

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 100%, so the three parameters are already fully documented in the schema, including partial/case-insensitive name matching and the 0-50 commit bound. The description only indirectly echoes them via "derniers commits" and "arborescence de surface," adding no syntax or trade-off guidance beyond the schema, so the 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?

The description opens with a specific verb-and-resource statement ("Fiche complète d'UN projet") and then enumerates the exact payload: path, remote repo, tech stack and notable dependencies, inferred role, detailed git state, recent commits, branches, context documents, and surface tree. The capitalized "UN" and the explicit mention of lire_cerveau make it distinguishable from lister_projets (many projects) and from file-content readers.

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?

It states exactly when to reach for it: "quand tu sais déjà de quel projet tu parles et que tu veux tout savoir dessus d'un coup." It also gives the boundary and the follow-up — read files or advise François first, and chain with lire_cerveau only if you need the actual CLAUDE.md/README content. Both the positive trigger and the exclusion are explicit.

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