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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the safety profile is handled. The description adds real behavioral context beyond them: results include the source document, a 'coverage' indicator discloses whether all policies or only closest matches were returned, and the not_found outcome when nothing is published is stated up front.

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, front-loaded with the core purpose before the query-mode caveat and the failure case. Dense but every sentence carries information; the parenthetical about 'all of them ... else closest matches' is slightly packed but earns its place by explaining coverage.

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?

An output schema exists, so return-value structure needn't be described, and the description still helpfully flags coverage and not_found. What is missing is any meaning for three of the four parameters and any sibling routing guidance, which leaves gaps for a tool sitting next to check_against_policy and ask_knowledge.

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 0% and all four parameters are undocumented in the schema, so the description carries the full burden. It explains only 'query' (applicability matching, ranking behavior) and leaves policy_id, category and limit completely undefined, so an agent cannot tell whether policy_id fetches a single policy or how limit interacts with the 'all of them when few' behavior.

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 and resource ('Get your department's current policies with their source document'), which is far clearer than the bare name. It implicitly separates itself from check_against_policy (evaluation) and ask_knowledge (Q&A), but never names those siblings explicitly, so the differentiation is inferred rather than stated.

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 explains the two usage modes well: no query returns all current policies, a query returns applicable policies ranked by relevance with 'coverage' signaling whether the set is complete. However, it gives no guidance on when to choose this over check_against_policy or ask_knowledge, which is the main routing decision an agent faces among these siblings.

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