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

Annotations provide only readOnly/openWorld/idempotent hints. The description adds critical behavioral context: extraction is limited strictly to tool output, a verbatim evidence quote accompanies answers, and an explicit refusal with granular refusal_reason codes is returned when data cannot answer. This goes far beyond the structured 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 front-loaded: purpose, mechanics, return contract, usage guidance, and cost tradeoff appear in that order. Every sentence carries decision-relevant information for a complex tool, and the length is justified by the detailed refusal contract and explicit usage boundaries.

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?

With no output schema, the description fully defines the success shape (answer, evidence, confidence, source, fetched_at) and the refusal shape with a precise refusal_reason enum. It also covers when to use, how it differs from the cheaper sibling, and cost implications. Nothing required for correct selection or invocation is missing.

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 all parameters are documented as aliases for a single natural-language question. The description adds no novel parameter syntax or formatting, only contextualizing how the question is used internally (routing and argument filling). Baseline 3 applies due to high schema coverage.

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 a specific verb phrase: 'Hallucination-resistant answer mode for high-stakes reads.' It then contrasts itself with ask_pipeworx by explaining the same routing but grounded extraction using only tool results, which clearly distinguishes it from siblings like ask_pipeworx and ask_pipeworx_beta.

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: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' with concrete examples. It also names the alternative: 'prefer ask_pipeworx for casual lookups,' and adds the cost dimension ('Costs one extra LLM call') for tradeoff decisions.

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