Skip to main content
Glama

Sondages

sondages
Read-onlyIdempotent

Sondages d'intentions de vote tels que publiés, du plus récent au plus ancien, avec l'institut, les commanditaires, les dates de terrain, l'échantillon, la méthode, la marge d'erreur et le lien vers la notice. Jamais moyennés ni fusionnés. Masqués pendant la période légale d'interdiction qui précède chaque tour.

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": "sondages"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNombre maximal de résultats.
roundNoTour de scrutin : 1 ou 2.
sinceNoDate de début incluse, au format AAAA-MM-JJ.
candidateIdNoIdentifiant du candidat (voir « lister_candidats »).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, closed-world semantics, so the description's added value is what it discloses beyond them: output ordering, the exact field set returned, the no-averaging/no-merging guarantee, and crucially that polls are masked during the legal pre-round prohibition period (i.e. an empty response can be correct). It does not describe pagination behaviour or what happens at the limit boundary, which keeps it from 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?

Three sentences, front-loaded with the core statement, followed by the two short behavioural qualifiers. The field enumeration is long but each item is a returned attribute an agent would otherwise have to discover empirically, so it earns its place; slightly tighter phrasing would push this higher.

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?

There is no output schema, and the description compensates by listing the returned fields, the sort order, and the masking rule that explains empty results. With 100% schema coverage on the four optional filters and full annotation coverage, only minor operational details (pagination beyond limit, exact behaviour at max=50) are absent.

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 limit, round, since and candidateId are already documented in the input schema, including the round enum and the candidateId pattern with a pointer to « lister_candidats ». The description adds no parameter-level detail beyond the incidental phrase 'chaque tour', so the baseline of 3 applies.

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 specific resource (sondages d'intentions de vote tels que publiés) with explicit ordering (du plus récent au plus ancien) and enumerates exactly what each record carries: institut, commanditaires, dates de terrain, échantillon, méthode, marge d'erreur, lien vers la notice. The sentence 'Jamais moyennés ni fusionnés' separates it behaviorally from any aggregation/comparison sibling, so an agent can tell what it is and what it is not without opening the schema.

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?

Usage is implied rather than stated: the tool returns raw published polls, so an agent infers it should use this when it needs individual poll records rather than aggregated or comparative figures, but no alternative tool is named and no when-not condition is given. The blackout note does signal that results may legitimately be empty, which is useful context for deciding whether a zero result is an error.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources