Skip to main content
Glama

rundata.re · La Réunion en direct

Crues et rivières à La Réunion

crues_rivieres
Read-only

Vigilance crues de Vigicrues Réunion (DEAL), rivière par rivière, et hauteur d'eau et débit mesurés toutes les 5 minutes aux 29 stations des rivières et ravines de l'île, avec leur tendance et les crues historiques comme repères. Rappeler de ne jamais traverser un radier submergé. Pour : « la rivière des Galets est en crue ? », « il y a une vigilance crues ? », « niveau de la ravine Saint-Gilles ? ».

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": "crues_rivieres"
  }
}

Input Schema

NameRequiredDescriptionDefault
lieuNoUne rivière (« rivière des Galets », « ravine Saint-Gilles ») ou un lieu (« Salazie », « Saint-Benoît ») pour les stations proches. Vide = toute l'île.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / lieu / description
      Previous value: -"Une rivière (« rivière des Galets », « ravine Saint-Gilles ») ou un lieu (« Salazie », « Saint-Benoît ») pour les stations proches. Vide = toute l'île. / A river or a place; empty = whole island."New value: +"Une rivière (« rivière des Galets », « ravine Saint-Gilles ») ou un lieu (« Salazie », « Saint-Benoît ») pour les stations proches. Vide = toute l'île."
  2. Changed1 schema field changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  3. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful operational context — 5-minute measurement cadence, 29 stations, historical flood baselines for interpretation, and a safety advisory about not crossing a submerged radier — but says nothing about data staleness, availability during cyclone events, or what happens when a station is offline.

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 description is front-loaded with what the tool returns and the data sources, then closes with illustrative queries. It is dense but every sentence, including the safety note, carries relevant information; no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With one optional parameter, no output schema and existing annotations, the description covers sources, granularity, and intended questions well. It stops short on the practical details an agent needs at call time, such as freshness of the vigilance bulletin versus the station readings and how empty or partial results should be interpreted.

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 coverage is 100% and the single optional parameter is fully documented, including that empty means the whole island. The description adds no syntax, naming, or matching guidance beyond what the schema already states, so the baseline 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 names the specific source (Vigicrues Réunion / DEAL) and the specific data resources: per-river flood vigilance, water height and flow measured every 5 minutes at 29 stations, plus trends and historical flood benchmarks. That is enough for an agent to distinguish it from weather-alert siblings such as vigilance_meteo, though it never names that alternative 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?

Three concrete example questions (river in flood, flood vigilance in effect, ravine level) give clear context on when to reach for this tool. There are no exclusions or pointers to sibling tools for adjacent needs like weather alerts or rainfall forecasts.

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.