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

Annotations already mark the tool read-only, idempotent, and non-destructive. The description goes well beyond that by revealing the internal routing behavior, the extra LLM call cost, the exact success return shape, and the explicit refusal object with its possible refusal reasons. No contradiction with the 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 but every sentence contributes: purpose, behavior and return contract, usage guidance, and cost comparison. The key differentiator—grounded extraction and refusal behavior—is front-loaded, with no filler or repetition of schema content.

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 routing tool with no output schema, the description fully covers success and failure behavior, the return payload, all refusal reasons, and when to choose this tool versus ask_pipeworx. An agent has enough information to invoke it correctly and interpret its results.

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%, and the input schema already documents the 'question' parameter and all aliases clearly. The description does not add parameter-level details beyond what the schema provides, so the high-coverage baseline of 3 applies.

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 'Hallucination-resistant answer mode for high-stakes reads' and clearly explains that it routes like ask_pipeworx but extracts answers using only the tool result, refusing when the data does not directly answer. This makes the tool's specific behavior and its distinction from ask_pipeworx immediately clear.

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 it: whenever an answer will be quoted, cited, or acted on, and facts must not be invented. It also gives the alternative and the trade-off: 'prefer ask_pipeworx for casual lookups' because this mode costs 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.