Skip to main content
Glama
Sign In

rundata.re · La Réunion en direct

by re.rundata
OverviewDiscussionsAdmin

Sites publics de La Réunion sans réponse

sites_sans_reponse
Read-only

Sites publics de La Réunion (974) qui ne répondent pas en ce moment, revérifiés chaque jour : pour chacun, depuis quand, le dernier constat en mots simples et ce qui manque donc sur rundata.re (avis de coupure d'eau, bulletins du volcan, houle…). Un site qui répond de nouveau sort de la liste. Ne dit jamais pourquoi un site se tait. Pour : « le site de l'OVPF marche ? », « pourquoi pas de bulletin du volcan ? », « le site de Sudéau ne répond plus ? ».

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": "sites_sans_reponse"
  }
}

Input Schema

NameRequiredDescriptionDefault
quoiNoUn site, une commune ou un thème : « volcan », « eau », « Saint-Joseph ». Vide = toute la liste.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / quoi / description
      Previous value: -"Un site, une commune ou un thème : « volcan », « eau », « Saint-Joseph ». Vide = toute la liste. / A site, a commune or a theme; empty = the whole list."New value: +"Un site, une commune ou un thème : « volcan », « eau », « Saint-Joseph ». Vide = toute la liste."
  2. Changed1 schema field changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  3. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already establish read-only, non-destructive, open-world behaviour, yet the description still adds real value: daily re-verification cadence, the churn rule that a site which responds again leaves the list, and an explicit epistemic limit (it never explains why a site is silent). It does not discuss pagination, ordering, or what an empty result means, so it is strong but not exhaustive.

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?

One dense paragraph, front-loaded with the resource and its freshness rule, then behaviour, then example queries. Every sentence carries information, though the three quoted example questions make it longer than strictly necessary for a single-optional-parameter tool.

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?

For a one-optional-parameter read tool with annotations but no output schema, the description supplies the missing return-shape information (per-site duration, last observation, missing content), the freshness guarantee, the list-membership rule, and the limitation. An agent can decide to call it and interpret results without further inference.

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% and the single optional parameter 'quoi' is already documented with its own examples and the empty-value semantics. The description adds no additional syntax or matching rules beyond that, so the schema carries the burden and the baseline of 3 applies.

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 states a specific resource and condition: public sites in Réunion (974) that are currently not responding, plus what is exposed per site (how long, last observation in plain words, what is consequently missing on rundata.re). The parenthetical examples (water-cut notices, volcano bulletins, swell) carve out its territory relative to data-domain siblings, though it never names a sibling tool explicitly.

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?

Concrete trigger phrases are given ("le site de l'OVPF marche ?", "pourquoi pas de bulletin du volcan ?", "le site de Sudéau ne répond plus ?"), which tells the agent exactly which user questions route here. It also sets a hard exclusion with "Ne dit jamais pourquoi un site se tait", but stops short of naming the tool to use instead for the underlying cause (e.g. coupures_eau, volcan_seismes).

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

All rundata.re · La Réunion en direct toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources