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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false; the description adds beyond that by disclosing that results are ranked by iNaturalist observations and returned as a single page of card-sized records. This provides ordering and result-shape context that the annotations do not cover.

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?

Three sentences, each carrying distinct information: search modes, filters, ranking, and record shape. It is front-loaded with the action and avoids filler.

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 covers the main decision points (query modes, filters, ordering, output unit) and an output schema exists to define return details. It does not explicitly mention that q is optional or contrast with sibling tools, but the schema/context signals cover the optional nature.

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 43%, and the description compensates by clarifying the q parameter accepts either common-name text or scientific names and by naming the optional category, habitat, and country filters. It does less for per/page pagination semantics, so it is strong but not complete.

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 the exact action (search species) and specifies input modes (free text in eight languages or scientific name) and filters, which sets it apart from the sibling get_animal detail tool. It is a specific verb+resource statement, not a tautology.

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?

It clearly conveys when to search: for species matching free text/scientific name, with optional filters, and notes the output is a page of card-sized records. It does not explicitly say to use get_animal for single-record details or list_categories/list_countries for metadata, so it lacks explicit alternatives.

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