Prévision météo à La Réunion

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

Annotations already declare readOnly/idempotent/non-destructive/open-world, so the safety profile is covered. The description still adds real context beyond that: it is a model forecast not an observation, every answer is labelled as such with stated limitations (microclimates invisible), and the confidence field is ensemble agreement of 51 ECMWF scenarios rather than a probability. It does not describe latency or failure behavior when a place name is ambiguous.

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?

Front-loaded with the core statement (forecast, model, scope, contents) before examples and edge cases. It is long and the French/English duplication plus four quoted phrasing examples are somewhat redundant, but each block still carries decision-relevant information.

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?

With no output schema, the description carries the return-shape burden and does so: daily granularity, 3-hour slices, altitude-adjusted temperatures, UV, confidence levels and the conditional mer_de_nuages block. Caveats (label as forecast, cyclone handoff) close the remaining gaps for a read-only forecast tool.

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%, so the baseline is 3; the description nevertheless adds meaning the schema does not: temperatures are re-scaled to the location's altitude, and in the Hauts above 800 m an extra 'mer_de_nuages' block with 6–9 h and 9–12 h windows is returned. That clarifies how 'lieu' changes the response shape, not just its syntax.

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 resource (weather forecast), its source (numerical model, not a measurement), its scope (a place in Réunion, tonight through 7 days) and its output content (sky, min/max temps adjusted to altitude, rain, wind/gusts, per day and 3-hour slices, UV, per-day confidence). It explicitly separates itself from meteo_actuelle for current conditions.

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 concrete user-phrasing examples ('will it rain tomorrow in Saint-Denis?', 'this weekend in Cilaos?') that map directly onto the tool, plus a named alternative (meteo_actuelle) for present conditions and a routing rule (cyclone → Météo-France official vigilance). When-to-use and when-not-to-use are both explicit.

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