Skip to main content
Glama

NLocale

Rechercher des lieux documentés

rechercher_lieux
Read-onlyIdempotent

Patrimoine et lieux dont les faits publics sont documentés. Filtrer par commune, code INSEE, catégorie et langue. Une vérification documentaire ne constitue pas une visite. Chaque résultat donne l'URL canonique, les sources et les dates disponibles.

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": "rechercher_lieux"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNombre maximal de résultats, de 1 à 20. Défaut : 10 (20 pour agenda_weekend).
queryNoMots recherchés, 160 caractères au plus. La recherche porte aussi sur les termes français de la même publication ; la réponse reste dans la langue demandée.
langueNoLangue de la réponse : fr, en, de, nl, it ou es. Défaut : fr. Une langue absente n'est pas remplacée par le français.fr
offsetNoDécalage de pagination. Défaut : 0. Le maximum est 500, sauf pour rechercher_articles_carnet (10000). La réponse donne pagination.total et pagination.next_offset.
communeNoNom de commune, 120 caractères au plus.
categorieNoCatégorie telle que publiée dans le catalogue, 120 caractères au plus.
insee_codeNoCode INSEE de commune, 5 caractères (chiffres ou lettres A-Z), par exemple 02408 pour Laon.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower; the description still adds value by describing the result payload (canonical URL, sources, available dates) and by warning that documented verification does not imply an actual visit. It does not discuss pagination behavior or result ordering, which the schema partly covers via offset.

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?

Four short sentences with no filler, moving from scope to filters to the semantic caveat to result contents. The telegraphic first sentence is slightly terse, but every sentence contributes and nothing 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?

For a 7-parameter, fully optional search tool with no output schema, the description covers scope, filtering axes, and the shape of returned data, which is the main gap an absent output schema would leave. What remains missing is guidance on choosing among the sibling search tools and any hint about pagination or result volume.

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% and the parameters are richly documented (INSEE pattern with an example, limit range and defaults, offset cap, language enum with no-fallback rule). The description only echoes the filter names without adding syntax or edge-case meaning beyond the schema, so the baseline of 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?

The description identifies the resource concretely: heritage sites and places whose public facts are documented, with the filters available (commune, INSEE code, category, language) and what each result carries (canonical URL, sources, dates). The verb is carried only by the tool name ('rechercher'), and nothing distinguishes it from near-siblings such as rechercher_etablissements or rechercher_contenus_publics, so it stops short of a 5.

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?

It states how to narrow a search ('Filtrer par commune, code INSEE, catégorie et langue') and adds a semantic caveat that a documentary check is not a visit, which implies the intended reading of results. However, there is no explicit when-to-use/when-not guidance and no named alternative for the many sibling search tools, so selection is left to inference.

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