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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description goes well beyond them: exact success return shape, verbatim evidence quote, every refusal_reason enum value, and the extra-LLM-call cost. An agent can predict exactly what comes back on success and failure. No contradiction 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?

Dense and mostly front-loaded, with the core distinction (hallucination-resistant) first. Long but every clause carries information: routing behavior, return contract, refusal codes, use cases, cost trade-off. Loses one point only for length; it could be tightened slightly.

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?

Given there is no output schema in the provided context, the description compensates fully by specifying the success response shape, all refusal_reason enum values, and the extra-call cost. It also names the sibling and gives selection criteria. Nothing an agent needs for correct invocation is missing.

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 100% (single required `question` with aliases), so the baseline is 3. The description adds that the agent only needs to ask in natural language and the tool will route and fill arguments itself, but it doesn't add meaning about the question parameter itself beyond what the schema shows.

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 uses specific, action-oriented language: 'hallucination-resistant answer mode', 'EXTRACTS the answer using ONLY what the tool result contains', and 'returns {answer, evidence ...} or refusal'. It immediately conveys what the tool does and explicitly differentiates it from the sibling ask_pipeworx, so an agent can classify the operation without opening the schema.

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 concrete selection criteria: use when answers will be quoted, cited, or acted on and hallucination is unacceptable (financial verdicts, legal claims, medical lookups, public statements); prefer ask_pipeworx for casual lookups. Also discloses that this mode costs one extra LLM call, which is exactly the kind of trade-off an agent needs to choose correctly between siblings.

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