Skip to main content
Glama
MCP Assemblée nationale

MCP Assemblée nationale

by Toumi-Elyes

Accords Entre Groupes

accords_entre_groupes
Read-onlyIdempotent

Compute pairwise agreement rates between parliamentary groups on a sample of roll-call votes, filtered by topic or a recent period of up to 30 days.

Instructions

Taux d'accord entre groupes parlementaires, deux à deux, sur un échantillon de scrutins.

À utiliser pour une vue d'ensemble des convergences entre groupes : pour chaque paire, part des scrutins où les deux groupes ont la même position majoritaire. Indiquer sujet ou periode_jours (30 au plus). Calculé sur un échantillon borné, annoncé dans la méthode. Pour une législature close (legislature, 14 à 16), la période finit à son dernier scrutin.

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": "accords_entre_groupes"
  }
}

Input Schema

NameRequiredDescriptionDefault
sujetNoSujet en mots-clés (« retraites »), avec accents.
legislatureNoLégislature analysée, de 14 (2012) à 17 (en cours). Sans valeur : un sujet est cherché dans les titres publiés par CIVIX (16e et 17e), une période compte les derniers jours.
max_scrutinsNoNombre maximal de scrutins analysés (échantillon borné).
type_scrutinNoType de scrutin : `texte` (vote sur l'ensemble d'un texte), `article`, `amendement`, `autre` (motions, résolutions, suspensions de séance…) ou `tous`.tous
periode_joursNoJours à analyser.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the bar is lower; the description still adds real behavior: results come from a bounded sample announced in the method, and for a closed legislature (14–16) the window ends at its last scrutin. It omits how the sample is chosen or how ties/abstentions are treated, which would matter for interpreting rates.

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?

Four short sentences, front-loaded with the metric definition before usage and caveats; each sentence carries information. Slightly dense with the parenthetical constraints, but no filler.

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 usefully explains what a result row means (per pair, share of concordant scrutins), and covers the bounded-sample caveat and legislature edge case. It leaves the effect of `max_scrutins`/`type_scrutin` on reliability and the meaning of 'position majoritaire' (abstentions, ties) unexplained.

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 description coverage is 100%, so the schema already documents each parameter; baseline is 3. The description does add one thing beyond the schema – the implicit at-least-one-of `sujet`/`periode_jours` requirement, since the schema marks nothing required – but repeats the 30-day cap and the 14–16 legislature range already present in the schema.

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+resource: pairwise agreement rates between parliamentary groups over a sample of scrutins, and defines the metric explicitly ('part des scrutins où les deux groupes ont la même position majoritaire'). This clearly separates it from cohesion_groupes (intra-group) and accords_entre_deputes (deputy-level) among the siblings.

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 une vue d'ensemble des convergences entre groupes' gives an explicit use case, and 'Indiquer `sujet` ou `periode_jours` (30 au plus)' encodes a selection rule for the two optional inputs. It does not name a sibling alternative (e.g. positions_groupes or cohesion_groupes) for the when-not case, so not a 5.

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