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

Annotations cover only the safety profile (readOnly, idempotent, closed-world), while the description adds real operational context: a single non-paginated object, seeded reference values that change only on deploy, session-level cacheability, a ~10 minute cache, per-IP rate limiting, and retry-on-5xx guidance. This is substantial disclosure beyond the annotations and nothing contradicts them.

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?

Front-loaded with the purpose, then usage routing, then return and caching behavior. Every clause carries information, though the caching/rate-limit tail is packed densely into semicolon-separated fragments.

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-parameter reference-lookup tool with an output schema, the description covers everything an agent needs: purpose, sequencing relative to sibling list tools, return cardinality, cache lifetime, and failure handling. Nothing material is left to inference.

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 tool takes zero parameters, so the schema is empty and the baseline is 4 per the rubric. The description reinforces this ('It takes no parameters') and describes the return shape, but there are no parameter semantics to add beyond that.

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?

Starts with a specific verb and resource ('Discover the filter vocabulary for the knowledge base') and enumerates exactly what comes back: total counts plus the section, pillar, and source-domain values with counts. It is immediately distinguishable from siblings like list_esg_pages or get_server_info, which it names.

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?

Gives explicit antecedent guidance ('Call it before list_esg_pages or list_esg_resources so filters match real values') and routes a related need elsewhere ('for server version and health use get_server_info'). Both when-to-use and the alternative are stated, not implied.

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