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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds substantial behavioral context: it explains the internal process (routing, fetching, extracting), the refusal mechanism with explicit refusal_reason values, and the cost implication. It doesn't describe token limits or timeout, but it covers the most critical behaviors (refusal outcomes, cost). Given annotations carry the safety profile, a 4 is deserved for adding rich behavioral detail.

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 well-organized: it front-loads the core value proposition, then moves to usage guidance, return structure, refusal reasons, and tradeoff. Every sentence earns its place, no fluff. It's long but necessary given the complexity of the tool's behavior. Structure is effective with a clear paragraph flow.

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?

The description covers the tool's purpose, internal behavior, success format, refusal reasons, that it returns evidence, and cost characteristics. It mentions the output structure in the description itself, compensating for the lack of an output schema. Given the tool's complexity and the richness of the description, nothing essential is missing for an agent to decide to use it and understand what to expect.

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% (all six parameters are aliases for the same 'question' field, each with a description). The description does not add new parameter-level detail beyond stating 'natural language' questions, but it does reinforce that the question is the only input and implicitly that it should be phrased as a query. Since schema is fully descriptive, baseline 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 clearly states a specific verb ('answer' / 'extract') on a specific resource ('Pipeworx' tool network) with a distinctive scope: hallucination-resistant grounded answering. It names the sibling 'ask_pipeworx' and contrasts itself ('same routing... then EXTRACTS'), distinguishing it from alternatives. The purpose is 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 ('whenever an answer will be quoted, cited, or acted on'), gives domain examples (financial, legal, medical), and tells when NOT to use it ('prefer ask_pipeworx for casual lookups'). It also names the exact alternative (ask_pipeworx) and the cost tradeoff (one extra LLM call). This is exemplary guidance.

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