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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so safety is covered. The description adds useful behavioral context by noting the taxonomy is versioned, contains active categories, uses stable IDs, and is distinct from narrative-theme output. No contradictions with annotations.

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 with no filler: the purpose, the return content, and the downstream usage/alternative are all covered efficiently. The most important information is front-loaded.

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 zero-required-parameter discovery tool with safety annotations and no output schema, the description is sufficiently complete. It explains what is returned, how to use the results, and how it differs from a closely named sibling.

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 only parameter, context, is fully documented in the schema as 'Optional user context for consistency with other Perception discovery tools.' The description does not add parameter-specific guidance, but since schema coverage is 100%, the baseline of 3 is appropriate.

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 discovers the versioned subject taxonomy and returns active top-level categories with child subjects and stable IDs. It also explicitly distinguishes itself from perception_get_categories, so an agent can tell them apart.

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 tells the agent exactly how to use the returned IDs: with category_ids and subject_ids in perception_search_mentions. It also names the alternative tool, perception_get_categories, and clarifies the taxonomy is separate from that tool's narrative-theme distribution.

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