MCP Assemblée nationale

Votes Serres

votes_serres

Read-onlyIdempotent

Identify recent French National Assembly roll-call votes decided by a narrow margin, with configurable vote gap, period, and scrutiny type to surface tight outcomes.

Instructions

Scrutins au résultat serré (faible écart entre pour et contre) sur une période récente.

À utiliser pour repérer les votes qui se sont joués à quelques voix. Par défaut, ne regarde que les votes sur l'ensemble d'un texte ; type_scrutin permet d'inclure les articles, amendements ou tous les scrutins.

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": "votes_serres"
  }
}

Input Schema

Name	Required	Description	Default
`ecart_max`	No	Écart maximal entre pour et contre, en voix.
`max_scrutins`	No	Nombre maximal de scrutins analysés (échantillon borné).
`type_scrutin`	No	Type de scrutin : `texte` (vote sur l'ensemble d'un texte), `article`, `amendement`, `autre` (motions, résolutions, suspensions de séance…) ou `tous`.	texte
`periode_jours`	No	Nombre de jours à analyser, jusqu'à aujourd'hui (30 au plus).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 31, 2026

TDQS

A3.9/5.0

Behavior3/5

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

The annotations already establish the read-only, idempotent, non-destructive, open-world profile, so the lower bar applies. The description adds genuine scope information — the default type filter silently excludes article and amendment ballots — which an agent would otherwise miss. However, it never mentions that results come from a bounded sample (max_scrutins, capped at 60) rather than an exhaustive scan, which is the most consequential behavioral caveat here.

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, no filler: purpose first, then intended use, then the default-scope caveat. The most decision-relevant fact (default restriction to whole-text votes) is in the final position where it can't be missed.

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 4-parameter filtered-query tool with no output schema, the description covers purpose, scope and how to broaden it, which is largely sufficient. The notable omission is that the underlying dataset is a capped sample, so an agent could wrongly treat the returned tight votes as exhaustive for the period.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns above baseline by defining the notion of écart (gap between for and against) and by explaining the consequence of type_scrutin's enum, including 'tous'. It doesn't touch ecart_max, max_scrutins or periode_jours, but those are already well documented in the schema.

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 specific resource and a defining criterion: ballots with a small gap between for and against over a recent period, and it explains what "serré" means. That lets an agent understand the tool's output immediately. It doesn't name a sibling tool or explicitly contrast itself with scrutins_par_periode or tendances_scrutins, so it stops short of full differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"À utiliser pour repérer les votes qui se sont joués à quelques voix" gives a clear use case, and the second sentence is a real usage guideline: by default only whole-text votes are included, and type_scrutin must be widened to capture articles or amendments. No exclusions or named alternatives are given, which keeps it below a 5.

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