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

Beyond the read-only, idempotent, and non-destructive annotations, it discloses that answers are extracted only from tool result content, describes the exact success and refusal shapes, enumerates refusal reasons, and notes the extra LLM call cost. This materially informs an agent about hallucination safeguards and failure behavior.

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?

Although longer than a typical tool description, every sentence earns its place: purpose, mechanism, return/refusal contract, use cases, and cost tradeoff. It is front-loaded with the primary purpose and avoids boilerplate.

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?

For an answer-mode tool with no output schema, it is complete: it covers routing, grounding constraint, return fields, explicit refusal semantics, example refusal reasons, and the caller-facing cost tradeoff. An agent has enough context to invoke it correctly and interpret failure cases.

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% and the question/aliases parameter is already described in the schema, so the description does not need to compensate. The description adds no parameter-specific guidance; the high schema coverage keeps this at baseline 3 rather than lower.

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 line states a precise mode: 'Hallucination-resistant answer mode for high-stakes reads,' and the body explains the grounded extraction mechanism — route, fetch, then extract only from the tool result. It explicitly contrasts with ask_pipeworx by naming it as the alternative for casual lookups, so an agent can tell the two apart.

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: whenever the answer 'will be quoted, cited, or acted on' and facts must not be invented, with concrete examples (financial, legal, medical, public statements). It also gives the when-not-to-use rule and alternative: 'prefer ask_pipeworx for casual lookups' because this mode costs 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.