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

The description significantly expands on the annotations by disclosing the refusal mechanism, exact success and failure return shapes, refusal reasons, and the constraint that it uses ONLY the tool result. No contradiction with the readOnly, idempotent, openWorld, or non-destructive hints is present.

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?

The description is dense but every sentence earns its place: core behavior, return contract, use cases, and cost tradeoff. It is front-loaded with the most decision-relevant information and does not waste words.

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, the description fully compensates by specifying both success and refusal return structures, refusal reason enum values, and the conditions under which refusals occur. It also provides cost and alternative guidance, making the tool fully actionable for an agent.

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% and the sole real parameter, question, is fully documented along with aliases. The description adds no parameter-specific guidance, but the schema carries the full burden, so the baseline of 3 is appropriate.

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 opens with a specific value proposition ('Hallucination-resistant answer mode for high-stakes reads') and clearly differentiates from sibling ask_pipeworx by explaining the same routing but stricter evidence-based extraction. It states exactly what the tool does: route, fetch, extract using only tool result, and return grounded answer or refusal.

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?

Provides explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' with concrete domain examples. It also names the alternative: 'prefer ask_pipeworx for casual lookups,' including the tradeoff of one extra LLM call.

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