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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds real value by disclosing that the data is a published snapshot rather than live, and that source/freshness metadata is returned. The irrelevant 'Bridge data' sentence detracts slightly but the provenance disclosure is genuine behavioral context.

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 units line and return-metadata note are tight and front-loadable, but the 'Bridge data is published, not a live clearance calculation' sentence does not earn its place in a dive-site tool and can actively mislead. One of the four sentences is wasted or wrong.

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 single-parameter search tool with no output schema, the units convention, bbox ordering, freshness caveat, and note that source metadata is returned give an agent nearly everything it needs. Only the undocumented 'limit' default/max and the unexplained bridge sentence leave gaps.

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 0%, so the description must compensate. It does so well for the bbox parameter by spelling out the axis order 'west,south,east,north' and by disambiguating the two query modes (name vs. bbox), though it does not explain 'limit' or the nested query object shape.

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 first sentence gives a specific verb and resource: 'Search published dive sites by name or west,south,east,north bbox,' which clearly separates it from siblings like find_wrecks and find_reefs. However, the stray sentence 'Bridge data is published, not a live clearance calculation' is copied from a bridge tool and muddies what this tool actually returns.

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?

'Verify access and operating details with the facility' is a useful caveat about how to treat results, implying this is a discovery step rather than authoritative clearance data. But there is no explicit when-to-use or when-not-to-use guidance and no named alternative among the many find_* POI siblings.

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