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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantive context beyond them: data is regenerated twice a day, a stale flag means more than 36 hours old, results are ordered best-and-soonest, and day labels are resolved in each town's local time. Those are behavioral traits an agent cannot get from the schema or annotations.

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 purpose and the sister-tool pointer are front-loaded, which is good, but the core is one long run-on sentence with nested parentheses listing return fields. It is dense enough that key details (stale threshold, ordering) are easy to skim past.

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 does the work of enumerating return content (day, rating, spot, best time, surf description, forecast confidence, local day name, today's rating) and mentions sharing each town's url. The gaps are the undocumented limit and region parameters rather than missing result semantics.

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 description coverage is only 25%, and the description compensates for two of four parameters: within_days ('from today up to within_days ahead') and min_rating ('at least min_rating'). region and limit are never mentioned, so the agent gets no hint about regional scoping or what limit truncates.

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 and ranking rule: towns whose best day within the window meets min_rating, ordered 'best and soonest first', with the fields each result carries. It also explicitly distinguishes itself from surf_forecast (one town's full forecast), so an agent can route 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 an explicit trigger phrase ('where is it good right now / this weekend') and names the natural follow-up tool, surf_forecast, for drilling into a single town. That is a when-to-use plus an alternative, not just implied context.

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