check_policy

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

With no annotations, the description carries the full burden. It does disclose the key trait that no content is retrieved (side-effect-free, dry-run semantics), which is valuable. However it says nothing about auth requirements, whether calls are logged, rate limits, or what a refusal/test result looks like.

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?

Two short sentences, front-loaded with the action and then the rationale. No filler, redundancy, or repetition of the schema.

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 one-parameter tool with no annotations and no output schema, the description covers intent but omits what the caller gets back (presumably a policy/allowed decision) and any auth or logging behavior. It is adequate but leaves the return contract to guesswork.

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 the single 'question' parameter is undocumented. The phrase 'Test a question against...' implies the string is a natural-language question, which is a small amount of added meaning, but no format, length, or example guidance is offered.

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 (test) and object (a question against the policy gate), and the phrase 'without retrieving anything' distinguishes it from the retrieval siblings (answer_question, search_corpus, get_passage). It stops short of naming a sibling explicitly, so an agent must infer the contrast.

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?

'Useful for reviewing where the refusal boundary currently sits' gives one implied use case (dry-run a question before asking answer_question), but there is no explicit when-to-use/when-not guidance or named alternative. The routing to answer_question is left to inference.

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