Multi-model wind forecast for a spot

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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety burden is lifted. The description then adds real value by describing what comes back (consensus, spread, agreement, gust factor, shore relation, plus a gust diagnosis), which matters since there is no output schema.

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?

Two sentences, front-loaded with the core purpose, no filler. The long parenthetical model list is the only mild bloat, but it is genuinely informative for the models parameter.

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?

The description adequately covers output shape for a no-output-schema tool, but with 10 parameters and only 60% schema coverage, several params (hours_from/hours_to, facing_deg, sport) get no description-level support and no usage routing is offered.

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 60% and the description reinforces the spot_id preference and names the model families, which loosely maps to the 'models' parameter. It does not clarify latency, days/hours_from/hours_to interactions, or the meaning of the remaining undocumented params, so it only partially compensates.

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 names a specific verb and resource ('Hourly wind forecast from several weather models at once') and details the output. It distinguishes itself substantively from generic forecast tools by naming the models and the consensus/spread/gust-factor framing, but never explicitly contrasts itself with siblings like ride_windows or list_models.

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?

Beyond 'Pass spot_id when known,' there is no guidance on when to choose this tool over ride_windows, tides, or list_models. The when/when-not framing is absent; the model-cost nuance lives in the schema, not the description.

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