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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints. The description adds critical behavioral context beyond that: it returns {answer, evidence, confidence, ...} on success and detailed refusal_reason values on failure, and it discloses the cost of an extra LLM call. No contradiction with annotations; instead it complements them with operational details.

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 conveys essential information: what it does, when to use, the return contract, refusal reasons, and cost trade-off. It is longer than average but justified by the richness of the behavior. Could be slightly trimmed, but it's well-structured and front-loaded.

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 a tool with no output schema, the description fully specifies the success and failure return shapes, enumerates refusal reasons, names the alternative, and gives usage guidance. Nothing a caller needs to decide or interpret is missing.

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 coverage is 100%, so the schema already documents the 'question' parameter and its aliases. The description adds no parameter-specific semantics beyond the schema, which aligns with the baseline of 3 for fully documented schemas.

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 clear purpose: a grounded, hallucination-resistant answer mode that extracts answers solely from tool results, with explicit refusal behavior. It distinguishes itself from the sibling ask_pipeworx by emphasizing the evidence/refusal contract, making selection unambiguous.

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?

Explicitly states when to use (high-stakes reads where answers will be quoted or acted on) and when not (casual lookups, prefer ask_pipeworx). Names the alternative and gives the cost trade-off (one extra LLM call). This is model guidance.

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