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

Annotations already mark the tool readOnly, idempotent, and non-destructive, so the description adds meaningful behavior beyond them: it explains the refusal mechanism with explicit refusal_reason values, the exact success return shape including evidence as a verbatim quote, and the extra LLM call cost. This gives the agent a clear model of what will happen on both success and failure.

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 long but every sentence earns its place: purpose, mechanism, return shape, refusal behavior, use cases, and cost/alternative are each covered in a logical, front-loaded structure. The high-stakes examples and refusal enum are dense but necessary, and there is no filler or repetition of schema details.

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?

Despite having no output schema, the description fully specifies the success return fields and all refusal reason variants, so the agent knows what to expect. It also covers routing, source scope, when to use the tool, when not to use it, and the cost differential with the sibling, making it complete for a tool of this complexity.

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 schema already documents the required 'question' parameter and all five aliases clearly. The description does not add any parameter-level semantics beyond saying the question must be answerable from the source, which is a usage constraint rather than a parameter formatting detail. Baseline 3 is appropriate given the schema already carries the burden.

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, distinctive purpose: 'Hallucination-resistant answer mode for high-stakes reads,' and clarifies the mechanism: 'EXTRACTS the answer using ONLY what the tool result contains.' It explicitly distinguishes itself from the primary sibling, ask_pipeworx, by noting 'Same routing as ask_pipeworx' but with grounded extraction, 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?

Usage guidance is explicit and actionable: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' with concrete high-stakes examples listed. It also names the alternative for casual cases: 'prefer ask_pipeworx for casual lookups,' and even surfaces the cost 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.