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

The annotations already declare readOnlyHint/openWorldHint/idempotentHint, and the description adds substantial behavior beyond them: the exact success return contract, the refusal mechanism with all five refusal_reason enum values, the verbatim-evidence constraint, and the extra LLM call cost. No contradiction with the annotations; the refusal semantics in particular go well beyond what annotations reveal.

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?

Five sentences, each carrying a distinct load: purpose, mechanism, output/refusal contract, usage triggers, and cost trade-off. The differentiator is front-loaded ('Hallucination-resistant'), and the final sentence ends with a practical routing conclusion. There is no filler or restatement of structured data.

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 present, the description supplies the full return structure on both success and refusal paths — including the evidence-as-verbatim-quote detail and every refusal reason. Combined with usage policy, cost disclosure, and the grounded-extraction guarantee, nothing an agent needs to invoke it correctly 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 description coverage is 100% — both visible parameters (alias, question) carry their own descriptions, so the schema does the heavy lifting for parameters. The description adds no param-specific detail beyond reinforcing that the input is a natural-language question, matching the schema's own wording. The baseline 3 is correct here.

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 opening phrase 'Hallucination-resistant answer mode for high-stakes reads' states a specific purpose and mode. The description names the mechanism (picks the right tool from 5,738 across 1499 sources, fills arguments, fetches data, extracts the answer using ONLY the tool result) and explicitly contrasts it with the sibling ask_pipeworx, so an agent can distinguish this tool without opening any 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 an explicit trigger condition ('Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts') with concrete domains (financial verdicts, legal claims, medical lookups, public statements), and an explicit when-not-to-use rule with the named alternative ('prefer ask_pipeworx for casual lookups'). Routing guidance is fully spelled out.

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