Skip to main content
Glama
Sign In
MCP Assemblée nationale

MCP Assemblée nationale

by Toumi-Elyes
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Bilan Depute

bilan_depute
Read-onlyIdempotent

Summarize one French deputy’s vote breakdown—for, against, abstentions, non-voters, absent—and their alignment rate with their parliamentary group on a chosen topic or period.

Instructions

Répartition des votes d'UN député sur un échantillon et alignement sur son groupe.

Donne le nombre de pour, contre, abstentions, non-votants et scrutins absents de la liste des votes, ainsi que la part de votes conformes à la position majoritaire de son groupe. Indiquer sujet ou periode_jours. Sert à décrire, jamais à classer ou juger un député.

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": {
      "depute": "<depute>"
    },
    "name": "bilan_depute"
  }
}

Input Schema

NameRequiredDescriptionDefault
sujetNoSujet en mots-clés (« retraites »), avec accents.
deputeYesNom d'UN député (« Jérôme Guedj ») ou son `uid`.
legislatureNoLégislature : 17 par défaut ; les 14e, 15e et 16e sont aussi couvertes.
max_scrutinsNoNombre maximal de scrutins analysés (échantillon borné).
periode_joursNoJours à analyser.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With readOnly/idempotent/openWorld annotations already covering the safety profile, the description adds real context: results are computed on a bounded sample (max ~60 scrutins), 'scrutins absents' are counted as a distinct category, and the tool is explicitly descriptive rather than evaluative. It still doesn't say what happens when both sujet and periode_jours are given or how large the sample typically is in practice.

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, front-loaded with what is returned, then the filter hint, then the descriptive-only guardrail. Nothing repeats the schema or the annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

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 enumerates the return categories and the conformity share, which is exactly what an agent needs to decide whether to call it. Remaining questions (sample truncation semantics, empty-result behaviour) are minor for a read-only statistics tool.

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 rises above it by advising which optional filters to supply and by framing max_scrutins as a sample bound rather than a plain limit. It doesn't explain how the filters interact (e.g. subject search combined with a day window).

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?

States a specific verb+resource: the vote breakdown (pour/contre/abstention/non-votant/absent) of ONE deputy plus alignment with their group's majority position. The emphasis on "UN député" implicitly separates it from siblings like comparer_deputes and accords_entre_deputes, but no sibling is named explicitly.

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 line "Indiquer `sujet` ou `periode_jours`" gives a concrete filtering instruction, and "Sert à décrire, jamais à classer ou juger" bounds the intended use. However, there is no guidance on when to pick this over obtenir_depute, comment_a_vote, cohesion_groupes or tendances_scrutins for the same deputy.

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

Deploy Server

Other Tools