Météo mesurée en ce moment à La Réunion

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

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is covered. The description adds real behavioral context beyond them: it returns dated measurements bundled with the station name, its distance and altitude, plus a microclimate warning when the requested place differs (altitude, windward/leeward slope), and it explains the radar fallback where no rain gauge exists. Minor gaps remain (no note on resolution limits or what happens for unknown place names), keeping it below 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The measured-now purpose and the sibling routing are front-loaded, and every clause (station metadata, radar fallback, microclimate warning) earns its place. It is somewhat long and the French and English blocks partially restate each other, which is the only waste.

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

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

There is no output schema, so the description must carry return values — and it does: dated measurements, station identity, distance, altitude, and conditional microclimate warnings, plus the radar-rain supplement. For a single-parameter read tool this is fully sufficient to call and interpret.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With a single parameter at 100% schema description coverage, the schema already documents free-text place names, coordinate format, and that empty returns the whole island. The description only reinforces the notion of 'the most representative station for the requested place' without adding syntax or edge-case handling beyond the schema — baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: current MEASURED weather at Réunion, listing concretely what is reported (temperature, rain over 6 min/1 h, humidity, wind/gusts, pressure, present weather) and the station-selection logic plus radar rain at the exact spot. It explicitly contrasts itself with prevision_meteo, so an agent can separate it from the forecast sibling without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit natural-language triggers (« quel temps fait-il à Saint-Denis ? », « il pleut à Cilaos ? ») and an explicit exclusion plus alternative: for later today/this evening/this weekend use prevision_meteo. The when-to-use and when-not-to-use conditions are both stated.

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