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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses the exact success response shape ({answer, evidence, confidence, source, fetched_at, refusal_reason:null}) and the full refusal contract with all five refusal_reason values. It also reveals the extra LLM call cost and that it uses the same routing as ask_pipeworx but then grounds the answer only in fetched results. This is rich, non-redundant behavioral disclosure.

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: definition, behavior, return contract, refusal contract, use cases, and cost tradeoff. It is front-loaded with the core differentiator and avoids filler or repetition of schema fields. The structural flow moves from identity to mechanics to usage guidance efficiently.

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?

Even without an output schema, the description fully specifies successful return fields, evidence behavior, refusal reasons and conditions, and the sibling tradeoff. It also provides enough operational context (routing, grounding, cost) for an agent to decide when to invoke this tool over ask_pipeworx. There are no critical gaps for correct selection and 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%, with the question parameter and all five aliases clearly documented. The description adds that the input is a natural-language question and that the tool internally fills arguments and fetches data, but it does not elaborate on parameter semantics beyond the schema. With full schema coverage, 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 precise verb and resource: 'Hallucination-resistant answer mode for high-stakes reads.' It clearly distinguishes this from the sibling ask_pipeworx by stating it 'EXTRACTS the answer using ONLY what the tool result contains' and by explicitly naming ask_pipeworx as the alternative. The scope, behavior, and refusal semantics are all specified in concrete terms.

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 explicit when-to-use guidance: 'whenever an answer will be quoted, cited, or acted on' for high-stakes domains like financial verdicts, legal claims, medical lookups, and public statements. It also states when NOT to use it: 'prefer ask_pipeworx for casual lookups' because this mode costs one extra LLM call. This directly routes an agent between the two siblings without ambiguity.

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