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

Annotations already mark this as read-only, open-world, idempotent, and non-destructive, and the description adds meaningful behavior beyond that: exact success and refusal return shapes, enumerated refusal reasons, the fact that the answer must come only from the tool result, and the extra computational cost. There is 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?

The description is dense and front-loaded with purpose and usage guidance, and each major section earns its place: return contract, refusal contract, use cases, and cost tradeoff. It is slightly longer than minimal due to routing statistics and full refusal-reason enumeration, which are useful but not all strictly necessary.

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?

Even though there is no output schema, the description fully documents what will be returned on success and failure, including field names and refusal reasons. Combined with the rich annotations and complete parameter schema, an agent has everything needed to select, invoke, and interpret this tool correctly.

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%: the single meaningful parameter, question, is fully described in natural language, and the aliases are all documented. The description adds general context about high-stakes use but not parameter-level details, so the schema-driven baseline 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 leads with a specific, distinctive purpose: 'Hallucination-resistant answer mode for high-stakes reads.' It differentiates from ask_pipeworx by stating it uses the same routing but extracts the answer only from the tool result, so an agent can tell which grounded variant to use.

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 criteria are explicit: use when the answer will be quoted, cited, or acted on and the agent must not invent facts, with examples in parentheses. Negative guidance is also given: 'prefer ask_pipeworx for casual lookups,' along with the concrete extra-LLM-call cost that justifies the choice.

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