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

Annotations already declare readOnly, idempotent, non-destructive, open-world. The description adds real behavior beyond that: the windFrom fallback bucket (windNotNamed), the return of global rules and whether any kite law exists, and the citation instruction. Missing: pagination behavior beyond the limit param, ordering, and whether results are deduplicated.

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-loads identity and call-to-action reasonably, but the middle is an over-long list of returned fields crammed into one sentence, and the 'cite the spot's url' instruction trails as a fragment. It is dense but not wasteful; tighter grouping of what-is-returned vs how-to-filter would help.

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?

No output schema exists, so the description must describe returns – and it does, enumerating the fields. It covers cross-tool routing, global rules, and the kite-law query. It stops short of pagination/truncation behavior and whether the 'rules that apply everywhere' are always returned or limited, leaving a small but real gap for a 6-param open-world catalog 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 50%, but four of six params are enums the schema already enumerates. The description compensates where the schema is silent: windFrom is a 16-point compass direction with 'spots a source names that wind for' semantics, and region is implicitly sport/local. limit is not discussed in the description, and level/water/sport get no extra meaning beyond their enums, keeping it at 4 rather than 5.

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: 'Puerto Rico's kite, wing and windsurf spots' and enumerates exactly what each result carries (sports, wind directions, water, level, launch, hazards, rules, schools, station, NWS zone). Easily distinguished from siblings find_surf_breaks and water_conditions_now by sport and by the explicit now-vs-catalog split.

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?

Explicitly routes: 'For the wind blowing now, use water_conditions_now.' Also tells the agent what the windFrom filter does and what happens when no direction is named (returned in windNotNamed), so filter behavior is predictable rather than inferred.

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