Température de la mer à La Réunion

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), and the description adds real context beyond them: it reports the source (buoy vs satellite), the measurement date and the distance — details an agent needs to judge freshness and trustworthiness. It doesn't address what happens when no measurement exists.

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 core claim and sample queries are front-loaded and the return content is stated compactly. The full English restatement doubles the length for little added information, though it does serve bilingual routing.

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?

For a one-parameter read tool with no output schema, the description supplies what the schema and annotations cannot: the nature of the returned measurement and its provenance fields. Only empty-result or no-coverage behavior is left unstated.

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?

Schema coverage is 100% and the single 'lieu' parameter is fully documented in the schema, so the baseline of 3 applies. The description's sample place names ('Saint-Leu', 'l'Hermitage') echo the schema's own examples rather than adding new syntax guidance.

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?

The description states a specific verb and resource ('Température de l'eau de mer MESURÉE à La Réunion') and scopes it to beaches or coastal places, which separates it from meteo_actuelle and prevision_meteo among the siblings. The capitalized MESURÉE plus the sample questions make the intent unmistakable.

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?

Three natural-language example queries plus 'Renvoie la dernière mesure disponible' give a clear picture of when this tool applies. It never names an alternative sibling or states when not to use it, so it stops short of the 5 bar.

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