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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by specifying that data comes from iNaturalist.org and does not require authentication, which is useful context beyond annotations. However, it doesn't disclose potential behavior like rate limits or that the result is ranked by observation count, which is partly in the schema for per_page. No contradiction.

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 description is two sentences, efficient and directly to the point. The first sentence gives purpose and filtering options, the second gives a use case and data source. No fluff, but it could be slightly more structured if needed. It earns a 4 because it is concise without being terse.

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?

Given the output schema exists (as per context signals), the description needn't explain return details. It covers the essential inputs (place_id from a sibling, filters) and adds the use case. It's complete enough for an agent to invoke correctly, though it could mention pagination behavior or that place_id is required from places_search, but that's in the schema.

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 100%, so all five parameters have descriptions. The description adds a small amount: it clarifies that taxon_id can filter to 'only birds or only plants' and that ranking is by observation count. But this largely reiterates the schema. Baseline 3 is appropriate because the schema already documents parameters well.

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 clearly states the tool's purpose: 'Get a biodiversity summary for a place' – it specifies the resource (place), the action (get species counts), and the ranking mechanism (by observation count). It also mentions the optional filters (taxon group, date range) and differentiates itself from siblings like inaturalist.observations.search and inaturalist.places.search by focusing on species counts rather than raw observations or place lookup.

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?

The description implies when to use it: 'Useful for surveying local wildlife or flora' and mentions it can be filtered to a taxon group. However, it doesn't explicitly state when NOT to use it (e.g., when raw observations are needed) or name alternatives like inaturalist.observations.search. It provides clear context but lacks explicit exclusions.

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