Skip to main content
Glama
MCP Assemblée nationale

MCP Assemblée nationale

by Toumi-Elyes

Tendances Scrutins

tendances_scrutins
Read-onlyIdempotent

Analyze recent French National Assembly voting trends over a chosen period, including weekly vote volume, adoption rates by type and context, and busiest days.

Instructions

Tendances générales des scrutins de l'Assemblée sur une période récente.

Pour une législature close (legislature), la période se termine à son dernier scrutin.

À utiliser pour les questions d'ensemble (« que s'est-il passé à l'Assemblée ce mois-ci ? », « combien de votes, quelle part d'adoption ? ») plutôt que pour un vote précis. Donne le volume de scrutins par semaine, la part de scrutins adoptés au total, par type (amendements, articles, ensembles de textes) et par contexte (PLF, PLFSS, propositions de loi), et les jours les plus chargés.

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": "tendances_scrutins"
  }
}

Input Schema

NameRequiredDescriptionDefault
legislatureNo
periode_joursNoNombre de jours à analyser, jusqu'à aujourd'hui.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, and open-world behavior, so the description's job is to add context. It does: the closed-legislature rule ('la période se termine à son dernier scrutin') is genuine behavioral information not captured by any structured field. It does not discuss limits or performance, but no contradiction with annotations exists.

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?

The opening sentence states the purpose, the second handles the legislature edge case, and the third gives usage plus output contents. It is well front-loaded and dense with useful information, though the output enumeration sentence is long and could be tightened.

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?

With no output schema, the description must sketch return values, and it does so concretely (volume hebdomadaire, part d'adoption globale/par type/par contexte, jours les plus chargés). What is missing is the granularity of those breakdowns and whether results are grouped or ranked, which would help an agent format answers.

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?

Both parameters are documented in the schema, though coverage is reported at 50%, and the description adds meaningful interaction semantics: for a closed legislature, periode_jours effectively truncates at the last scrutin. However, it never mentions the 7–90 day bounds, the 30-day default, or how legislature null selects the current one, so it does not fully compensate for the coverage gap.

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?

The description states a specific resource (scrutins de l'Assemblée) and an aggregate analysis (tendances générales, volume par semaine, part d'adoption par type et contexte). It explicitly distinguishes the tool from single-vote tools like obtenir_scrutin by saying it is not for 'un vote précis'.

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?

It gives an explicit when-to-use with example questions ('que s'est-il passé à l'Assemblée ce mois-ci ?', 'combien de votes, quelle part d'adoption ?') and an explicit when-not-to-use ('plutôt que pour un vote précis'). It also notes the special case for closed legislatures where the period ends at the last scrutin.

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