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

Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds meaningful behavioral context beyond those: it enumerates the specific fields returned, discloses that higher-classification breadcrumbs are NOT included, and offers a strategy to work around that limitation. This is exactly the kind of value-added disclosure that helps an agent understand what to expect from the call.

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 front-loaded with the core purpose, then adds a compact field inventory, then gives a targeted sibling comparison and usage workaround. Every sentence earns its place; nothing is redundant or extraneous. It is longer than typical but justified by the sibling complexity.

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 one parameter, 100% schema coverage, rich annotations, and an output schema, the description covers all essential context: input acquisition, expected return fields, a notable limitation, and how to work around it. The agent has everything needed to call this tool correctly.

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?

The input schema has 100% coverage: taxon_id is documented as the Catalogue of Life usage ID with an example and a note to obtain it from prior search/suggest results. The description repeats this workflow guidance, adding a little value by specifying the sibling calls (col.species.search / col.species.suggest) but no substantial new meaning beyond the schema.

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 ('Retrieve'), a specific resource ('full taxonomic details for a specific taxon in the Catalogue of Life'), and the exact input ('COL usage ID'). It also differentiates itself from col.species.search by explicitly noting the difference in returned breadcrumbs. Clear enough for an agent to distinguish from siblings.

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?

Provides explicit workflow guidance: obtain taxon_id from col.species.search or col.species.suggest, and if ancestors are needed, use parent_id or pass the scientific name to col.species.search with a rank filter. This explains when to use this tool versus col.species.search and how to fill gaps, leaving little to inference.

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