Skip to main content
Glama

Aides à la rénovation énergétique (France)

Chercher dans les dossiers publics

rechercher_connaissances
Read-onlyIdempotent

Cherche dans les dossiers d’aides, guides et fiches publics de Visitech (rénovation énergétique, CEE, MaPrimeRénov’). Rend les passages les plus proches, avec l’identifiant de leur fiche.

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": {
      "question": "<question>"
    },
    "name": "rechercher_connaissances"
  }
}

Input Schema

NameRequiredDescriptionDefault
limiteNoNombre de passages, 8 par défaut.
questionYesQuestion ou mots-clés, en français.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds retrieval behavior beyond that: results are semantically nearest passages, not whole documents, and each passage carries its fiche identifier — a useful bridge to the read tool. It does not say what happens on no match or how ranking works.

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?

Two tight sentences: scope first, then return behavior. Zero filler and no repetition of the title.

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 two-parameter read-only search tool with full schema coverage and annotations, the definition covers corpus scope and return shape adequately. A brief hint about what to do with the returned identifier (e.g., lire_fiche) would close the remaining gap.

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 both parameters (question, limite with default 8) are already documented in structured data. The description adds nothing about the query format or the result-count limit, so the baseline 3 applies.

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?

States a specific verb ('Cherche') plus the resource scope: public aid documents, guides and fiches from Visitech, with the domain named (rénovation énergétique, CEE, MaPrimeRénov'). It also distinguishes itself from listing/reading siblings indirectly by noting it returns 'les passages les plus proches' with a fiche identifier. It stops short of explicitly contrasting with lire_fiche or lister_fiches.

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: this is the tool for a natural-language question about aid content. There is no explicit when-to-use/when-not guidance, no note that it is French-query-only beyond what the schema says, and no routing to siblings such as lire_fiche for full fiche content or lister_fiches for browsing.

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