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

The description discloses important non-obvious behaviors beyond the annotations: it will not invent facts, returns explicit refusal reasons, uses only tool-result content, and requires an extra LLM call. These details add real value on top of the readOnly/openWorld/idempotent hints. No contradiction with annotations.

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?

Though detailed, every sentence earns its place: mode, process, success response shape, refusal contract, usage criteria, and cost tradeoff. The core purpose is front-loaded, and there is no 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?

With no output schema, the description compensates thoroughly by specifying exact success fields and every refusal_reason enum value. It also covers the key decision factor (high-stakes vs. casual lookups) and the extra-call tradeoff, leaving nothing essential for an agent to guess.

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%: the question parameter and all aliases are already described. The description adds no parameter-specific semantics beyond the tool's routing behavior, which is appropriate because the schema carries the parameter meaning.

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, distinct capability: 'hallucination-resistant answer mode for high-stakes reads.' It clearly differentiates from the sibling ask_pipeworx by explaining it extracts answers only from tool results, returns evidence/refusals, and costs an extra LLM call.

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 states when to use the tool ('whenever an answer will be quoted, cited, or acted on') with concrete high-stakes examples, and when not to ('prefer ask_pipeworx for casual lookups'). This directly guides routing among siblings.

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