Skip to main content
Glama
MCP Assemblée nationale

MCP Assemblée nationale

by Toumi-Elyes

Accords Entre Deputes

accords_entre_deputes
Read-onlyIdempotent

Compare pairwise voting agreement among 3–5 named deputies on a sample of roll-call votes, showing for each pair the share of votes cast the same way.

Instructions

Compare les votes de 3 à 5 députés nommés, deux à deux, sur un échantillon de scrutins.

À utiliser pour « Ces députés votent-ils pareil ? » avec plus de deux personnes : pour chaque paire, part des scrutins votés de la même façon parmi ceux où les deux ont exprimé un vote. Pour deux députés, préférer comparer_deputes. Indiquer sujet ou periode_jours. Description factuelle d'un échantillon borné, sans jugement.

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": {
      "deputes": "<deputes>"
    },
    "name": "accords_entre_deputes"
  }
}

Input Schema

NameRequiredDescriptionDefault
sujetNoSujet en mots-clés (« retraites »), avec accents.
deputesYesNoms (ou `uid`) de 3 à 5 députés, tous distincts.
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

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description nonetheless adds real behavioral context the annotations cannot convey: the denominator rule (share of concordant votes among scrutins where both voted) and the fact the sample is bounded and reported without judgment. It stops short of describing return shape or tie/abstention handling, keeping it below a 5.

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?

Front-loaded with the verb and scope, then usage, then the alternative, then parameter hints. Slight redundancy between 'sur un échantillon de scrutins' and the closing 'échantillon borné, sans jugement', but each sentence still carries distinct information.

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, yet the description explains the core reported metric (per-pair concordance rate) adequately for correct invocation, and all five parameters are schema-documented. It leaves minor gaps on result ordering and on how the bounded sample is chosen.

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 baseline is 3, but the description adds selection guidance beyond the schema by telling the caller to indicate sujet or periode_jours. It does not clarify how sujet and periode_jours interact when both are given, which limits it to a 4.

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?

States a precise verb (compare), resource (votes of 3-5 named députés), method (pairwise) and scope (bounded sample of scrutins). It explicitly distinguishes itself from the sibling comparer_deputes by the number of people involved, so an agent can route 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?

Gives a concrete user-intent trigger (« Ces députés votent-ils pareil ? » with more than two people) and names the alternative for the two-person case. It also tells the caller to supply sujet or periode_jours, which is actionable steering rather than implied usage.

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