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

Beyond the readOnly/idempotent annotations, the description reveals the refusal mechanism, the exact refusal_reason enum, the success response shape including verbatim evidence, and the extra LLM call cost. This adds substantial behavioral context for an agent deciding whether the tool is safe and appropriate.

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 information-dense but every sentence earns its place: purpose, routing, return/refusal contract, high-stakes use case, and cost comparison. It is front-loaded with the most important behavioral distinction and avoids filler.

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 thoroughly explains return values, success and refusal states, evidence extraction, and failure reasons. It also covers when to prefer the sibling tool, making the tool's full usage context self-contained.

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?

The input schema already provides 100% documentation coverage, including aliases for the single required question parameter. The description does not add parameter-level meaning beyond what the schema offers, so the baseline score 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 clearly states this is a grounded, hallucination-resistant answer mode that routes like ask_pipeworx but extracts answers only from the tool result. It distinguishes itself from the sibling ask_pipeworx by emphasizing evidence-based extraction and explicit refusals when data is insufficient.

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?

It explicitly says to use this tool when answers will be quoted, cited, or acted on, and names high-stakes domains like financial, legal, and medical lookups. It also tells the agent to prefer ask_pipeworx for casual lookups, citing the extra LLM call cost, which provides clear decision criteria.

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