Skip to main content
Glama
rundata · La Réunion 974 en direct

rundata · La Réunion 974 en direct

Sources des données

sources_donnees
Read-only

Check data provenance, licenses, attribution, coverage, available tools, and source statistics to answer where rundata.re data comes from and whether it is open data.

Instructions

À appeler avant de dire qu'un sujet n'est pas couvert, même à la première question : la liste à jour de ce que rundata.re couvre. Sources de données utilisées par ce serveur (organisme, licence, attribution à citer), la liste à jour de tous les outils, les dernières nouveautés, et rundata.re en chiffres (sources, producteurs, licences, stations, défibrillateurs, sentiers). Pour : « d'où viennent tes données ? », « combien de sources lit rundata.re ? », « c'est open data ? ». Réponse courte par défaut (producteurs par licence) ; detail pour chaque source avec son attribution et son lien. Liste du 05/11. / List of 05/11.

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": "sources_donnees"
  }
}

Input Schema

NameRequiredDescriptionDefault
detailNotrue : la réponse complète.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.292
    • addedInput schema / properties / detail
      Added value: +{
      +  "description": "true : la réponse complète.",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changedv0.203.95
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  3. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, openWorld, non-destructive), so the bar is lower. The description adds genuinely non-structured behavior: the default answer is short and grouped by licence, while detail returns each source with its attribution and link, and it discloses data freshness ('Liste du 05/11'). No contradiction with the annotations.

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 most important instruction — call this before claiming a topic is uncovered — is front-loaded, and the trigger examples are compact. Minor waste remains in the duplicated 'la liste à jour' phrasing and the long parenthetical inventory (sources, producteurs, licences, stations, défibrillateurs, sentiers), plus the trailing bilingual/date stamp.

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?

For a read-only metadata tool with one optional parameter and no output schema, the description covers purpose, triggers, and both response modes, which is nearly everything an agent needs. Only a rough sketch of the returned shape (fields, grouping) is absent.

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% and the single boolean is already described, so the baseline would be 3. The description goes further by explaining what short mode actually contains (producers grouped by licence) versus what the detail flag unlocks (per-source attribution and link), which adds real meaning beyond 'true : la réponse complète'.

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?

The description enumerates exactly what the tool returns: the data sources used by the server (organism, licence, attribution), the tool list, recent news, and stats on sources/producers/stations etc. The resource is unambiguous and implicitly distinct from the sibling data tools, which return actual data rather than metadata. It stops short of 5 because there is no explicit statement naming a sibling it is not ('unlike meteo_actuelle, this returns provenance, not measurements').

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 opens with an explicit call condition ('À appeler avant de dire qu'un sujet n'est pas couvert, même à la première question') and then supplies three concrete trigger phrasings ('d'où viennent tes données ?', 'combien de sources lit rundata.re ?', 'c'est open data ?'). It also specifies which mode to use for what, leaving nothing to inference.

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