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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description doesn't repeat those. It adds valuable behavioral context: the tool costs an extra LLM call, may return an explicit refusal instead of inventing answers, and specifies the refusal_reason enum. It also discloses the extraction-only-from-result behavior. One minor gap: it doesn't explicitly say what happens when the tool result is empty, but the refusal_reason enum covers data_truncated and not_in_source, which is sufficient.

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 compact and front-loads the key differentiator ('hallucination-resistant') and the routing behavior, then gives the return contract, refusal modes, and usage guidance. It packs a lot into a few sentences without redundancy. The only slight inefficiency is repeating 'ask_pipeworx' three times, but that serves the comparison purpose.

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 single-parameter tool with rich annotations (readOnly, idempotent, non-destructive) and no output schema, the description covers everything an agent needs: what it returns on success and failure, the refusal_reason enum, when to use it, and the cost tradeoff. The absence of an output schema is compensated by the detailed return contract. This is complete for the tool's complexity.

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 schema documents the 'question' property and its five aliases. The description adds that the question is 'natural language' and lists aliases, which slightly overlaps with schema but clarifies intent. Since the schema already fully documents the parameter, the description adds marginal value beyond it. 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 states a specific verb ('answer') with a distinguishing feature ('grounded', hallucination-resistant), and explicitly contrasts with its sibling 'ask_pipeworx' by naming it and describing the difference. It names the return contract and the refusal modes, so an agent can distinguish it from the other 33 siblings without ambiguity.

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 explicitly states when to use this tool ('whenever an answer will be quoted, cited, or acted on... must not invent facts') and when to prefer the alternative ('prefer ask_pipeworx for casual lookups'). It also names the sibling 'ask_pipeworx' as the alternative. This is exemplary usage guidance.

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