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

While annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, the description adds substantial behavior beyond them: the full refusal mechanism with all five refusal_reason values, the evidence-as-verbatim-quote guarantee, the internal pipeline (routing across 5,908 tools, filling arguments, fetching, then extracting), and the "data_truncated" refusal disclosing truncation behavior. The cost disclosure (one extra LLM call) is also behavioral context annotations cannot express. No contradiction exists between the description and 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?

The core purpose is front-loaded in the opening phrase, then flows logically: mechanism, success return shape, refusal return shape, when-to-use, and cost-based alternative. The description is dense but every sentence carries distinct operational information; the refusal_reason enum and the domain examples earn their place because there is no output schema to carry that burden.

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, the description compensates fully by documenting both the success shape ({answer, evidence, confidence, source, fetched_at, refusal_reason:null}) and the refusal shape with all possible refusal_reason values. The routing explanation, cost trade-off, and high-stakes usage domains make the tool correctly invocable and interpretable. Only minor details like the confidence scale are unspecified, which does not impede correct invocation.

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%, so the baseline is 3. The description mentions "fills arguments" but this refers to the internal routed tool's arguments, not the caller's parameters. It adds no extra meaning about the question format or timeout_seconds beyond what the schema already provides, so it does not exceed the baseline.

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 states a specific mode of operation: "Hallucination-resistant answer mode for high-stakes reads" that "EXTRACTS the answer using ONLY what the tool result contains." It clearly differentiates from the sibling ask_pipeworx by describing the same routing but grounded extraction, and explicitly names the alternative at the end. A verb, resource, and distinguishing behavior are all present.

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?

The description gives an explicit when-to-use rule: "Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts," with concrete domains listed (financial verdicts, legal claims, medical lookups, public statements). It also gives an explicit exclusion and alternative: "prefer ask_pipeworx for casual lookups," justified by the cost difference of one extra LLM call. Nothing 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.