MCP Assemblée nationale

Votes Scrutin

votes_scrutin

Read-onlyIdempotent

Retrieve individual deputy votes for a specific scrutin, grouped by position and filterable by parliamentary group, vote position, or name, with official totals to verify breakdowns.

Instructions

Votes individuels des députés sur un scrutin, regroupés par position.

Les totaux officiels sont toujours indiqués ; la liste de noms est limitée à 60 noms (utiliser groupe, position ou nom pour affiner). Pour savoir comment UN député a voté sur un sujet, préférer comment_a_vote.

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": {
      "uid": "<uid>"
    },
    "name": "votes_scrutin"
  }
}

Input Schema

Name	Required	Description
`nom`	No	Ne garder que les noms contenant ce texte (accents et casse ignorés).
`uid`	Yes	Identifiant du scrutin, par exemple « VTANR5L17V7324 » (obtenu avec rechercher_scrutins ou rechercher).
`groupe`	No	Ne garder que les députés de ce groupe (sigle, cf. lister_groupes).
`position`	No	Ne garder que cette position : pour, contre, abstention, non_votant.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 31, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior: official totals are always returned while the name list is capped at 60. It does not explain pagination beyond that cap, so not a full 5.

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 short sentences: what it returns, the 60-name limit with the filtering workaround, then the sibling redirect. Front-loaded and no redundant restatement 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?

No output schema exists, and the description compensates by describing the result shape (totals always present, names truncated). What remains unstated is whether the 60-name cap is per position or total, and what an unknown `uid` yields — minor gaps for a read-only tool.

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% and each parameter already carries its own description (including `uid` example and enum for `position`). The description only restates the three filter names as narrowing levers, adding no semantics beyond the schema — baseline 3.

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?

Specific verb+resource in the first clause: individual deputy votes on a given scrutin, grouped by position. It also names the sibling (comment_a_vote) it is not, so an agent can discriminate without opening either schema.

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?

Explicitly routes the agent: use `groupe`, `position` or `nom` to narrow the list, and prefer comment_a_vote when the question is how ONE deputy voted. Both the when and the alternative are stated.

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