answer_question

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

With no annotations, the description carries the full burden and does well: it discloses the policy-gate-then-retrieval flow, the three possible verdicts, and the specific behavior of 'referred' (no passages returned) and 'no_source' (threshold not cleared). It omits auth requirements, rate limits, and error/timeout behavior, keeping it from a 5.

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 tight sentences with the core purpose front-loaded and the verdict contract laid out efficiently. The parenthetical verdict explanations each earn their place, though the enumeration adds some density.

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 no output schema and no annotations, the description compensates by explaining the return contract via the three verdicts. It is nearly complete for an agent to call and interpret the tool, with the only gap being the undocumented max_passages parameter.

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 coverage is 50%: 'question' is documented as 'verbatim' and the description reinforces acting on its result, but 'max_passages' (with default 4, min 1, max 10) is never mentioned in the description. The bounds and default in the schema make it largely self-explanatory, so this lands at the baseline rather than a gap.

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 names a specific verb+resource ('answers the user's question') and outlines the internal pipeline (policy gate then retrieval), which distinguishes it from lower-level siblings like search_corpus and get_passage. It also frames itself as the 'Primary tool,' implicitly positioning it as the entry point. It does not explicitly name a sibling it differs from, so it stops short of a 5.

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 gives clear context for use ('Primary tool') and a strong directive on how to act on the result ('respect the verdict and must not answer from your own knowledge'). What's missing is explicit when-not guidance or naming of alternatives (e.g., when to drop to search_corpus or list_gaps).

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