MCP Assemblée nationale

Search

search

Read-onlyIdempotent

Find French National Assembly roll-call votes, legislative files, deputies, and groups by keyword, returning IDs and URLs for follow-up detail retrieval.

Instructions

Cherche scrutins, dossiers législatifs, députés et groupes (données CIVIX).

Renvoie un JSON {"results": [{"id", "title", "url"}]} ; les identifiants (scrutin:<uid>, depute:<uid>, groupe:<sigle>, dossier:<DLR…>) se passent à fetch.

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": {
      "query": "<query>"
    },
    "name": "search"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes	Mots-clés : sujet de vote, nom de député ou de groupe.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 31, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already establish that this is a read-only, idempotent, open-world search operation. The description adds meaningful behavioral context beyond the annotations: the output is a JSON object with `results`, each containing `id`, `title` and `url`, and the ID formats are documented for downstream `fetch` calls. It does not mention ranking, result limits or pagination, so it is not fully transparent.

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?

The description is two sentences, front-loaded with what is searched, followed by the return shape and ID handoff to `fetch`. Every sentence carries useful information and there is no redundant restatement of the tool name.

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, it is valuable that the description documents the return JSON shape and the identifier formats used by `fetch`. For a one-parameter search tool with safety annotations, this is mostly complete. The main missing piece is disambiguation from the many sibling search tools and any note about result limits or ranking.

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?

The single `query` parameter has full schema description coverage, including examples of keywords such as vote subject, deputy name or group name. The tool description reinforces the entity types being searched but does not add syntax, matching behavior or other semantics beyond the schema. With schema coverage at 100%, a 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?

The description states a clear verb and resource set: it searches scrutins, dossiers législatifs, députés and groupes. It also explains that result IDs are meant to be passed to `fetch`, which helps distinguish it from the fetch tool. However, it does not distinguish this generic `search` from sibling search tools such as `rechercher`, `rechercher_scrutins` or `rechercher_deputes`.

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?

The description implies a workflow: search here, then pass the returned identifiers to `fetch`. That is useful context, but it gives no explicit guidance on when to use this tool versus the many specialized search siblings. Usage is inferable but not clearly scoped.

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