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

The description adds substantial behavioral transparency beyond the annotations: it reveals that the tool will either return a structured answer with verbatim evidence and confidence, or explicitly refuse with a refusal_reason enumeration. It also discloses that it only uses the tool result and cannot invent facts. There is no contradiction with the readOnlyHint, openWorldHint, or idempotentHint 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 information-dense but every sentence contributes: purpose, behavior, return shape on success, refusal behavior, use cases, and cost tradeoff. The core distinguishing trait (grounded extraction) is front-loaded, and the alternative (ask_pipeworx) is mentioned with a concrete selection criterion. There is no filler or repeated 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?

This is a complex routing tool with no output schema, so the description correctly takes on the burden of specifying return values. It fully describes both the success return object and the explicit refusal object with all refusal reasons. It also covers when to use versus avoid it and the operational cost, making the description complete for an agent deciding whether and how to invoke it.

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 documents the question parameter and all five aliases (query, q, prompt, text, input) with 100% coverage. The description does not add parameter-level detail, which is acceptable because the schema fully carries that burden. The description's reference to routing and argument filling is contextual rather than parameter-specific, so a baseline 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 identifies this as a hallucination-resistant, grounded answer mode for high-stakes reads. It names the specific behavior (extracting the answer using ONLY what the tool result contains) and distinguishes itself from the sibling ask_pipeworx by stating it is 'Same routing as ask_pipeworx' but with grounded extraction. An agent can easily tell when this tool is the intended choice.

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?

The description is explicit: use this tool when an answer will be quoted, cited, or acted on and the agent must not invent facts, with concrete domains given (financial verdicts, legal claims, medical lookups, public statements). It also explicitly says to prefer ask_pipeworx for casual lookups because this costs one extra LLM call. This is strong when-to-use and when-not-to-use guidance.

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