rundata.re · La Réunion en direct

Marée à La Réunion

maree

Read-only

Hauteur de la mer mesurée chaque minute par les marégraphes du SHOM au Port (Pointe des Galets) et à Sainte-Marie : niveau actuel, marée montante ou descendante, dernières pleine et basse mer observées ; puis les prochaines pleines et basses mers sur deux jours, CALCULÉES par rundata d'après les mesures (pas la prédiction officielle du SHOM), à environ 15 à 20 min et 5 cm près : le dire, avec la précision donnée, et au-delà de l'horizon renvoyer au SHOM. Les heures calculées ne valent que près des deux marégraphes, à 15 km au plus. Plus loin, la marée arrive à une autre heure : l'outil donne alors la hauteur mesurée au marégraphe le plus proche, sans heures, et le lien vers les horaires officiels du SHOM. Pour : « la marée monte ? », « c'est quand la marée basse demain ? », « niveau de la mer au Port ? ».

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": "maree"
  }
}

Input Schema

Name	Required	Description	Default
`lieu`	No	Un lieu de la côte (« Le Port », « Saint-Gilles », « Sainte-Marie ») pour le marégraphe le plus proche. Vide = les deux.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 26, 2026

changedInput schema / properties / lieu / description

Previous value: -"Un lieu de la côte (« Le Port », « Saint-Gilles », « Sainte-Marie ») pour le marégraphe le plus proche. Vide = les deux. / A coastal place; empty = both gauges."New value: +"Un lieu de la côte (« Le Port », « Saint-Gilles », « Sainte-Marie ») pour le marégraphe le plus proche. Vide = les deux."

Changed1 schema field changedOct 26, 2026
- removedInput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```
AddedOct 24, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already establish that this is a read-only, non-destructive, open-world operation, and the description adds substantial behavioral context beyond that. It discloses the data source, that future tides are calculated by rundata rather than official SHOM predictions, the approximate accuracy of 15–20 minutes and 5 cm, and the fallback behavior outside the 15 km radius.

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 the data source and returned information, and every clause appears to carry useful operational detail. It is dense and semicolon-heavy in a single paragraph, so it could be easier to scan, but it avoids filler and does not merely restate the title.

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-parameter, read-only tool with no output schema, the description is complete: it explains what data is returned, how future tides are derived, the precision limit, the geographic validity limit, and what happens when the requested location is too far from a gauge. An agent has enough information to call it correctly and to communicate its caveats.

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%, so the basic meaning of lieu is already documented. The description adds useful semantics: the chosen place maps to the nearest tide gauge, an empty value covers both gauges, and locations beyond 15 km cause the tool to return measured height without calculated times.

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?

The description states a specific resource — sea height measured by SHOM tide gauges at Le Port and Sainte-Marie — and the exact information returned: current level, rising/falling state, last observed high/low, and next high/low tides over two days. It also distinguishes the calculated values from the official SHOM prediction, making the tool clearly identifiable among siblings such as temperature_mer or prevision_meteo.

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 gives explicit example questions that should trigger the tool and states when to redirect users to SHOM beyond the two-day horizon. It also defines geographic applicability: calculated tide times are valid only within 15 km of the two gauges; farther away, the tool returns only measured height at the nearest gauge with no times and a link to official schedules.

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 tools Inspect

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.