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

Beyond annotations, the description discloses critical behavioral traits: extraction uses ONLY the tool result, returns verbatim evidence, returns a structured refusal with enumerated refusal reasons when data doesn't answer, and costs an extra LLM call. These details go well beyond the readOnly/openWorld/idempotent 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 earns its place: it explains the mechanism, return contract, refusal behavior, use cases, and cost tradeoff. Key differentiators are front-loaded, and no filler or redundant restating of the schema is present.

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 tool with a simple single-question parameter and no output schema, the description fully specifies the expected return shape, refusal reasons, intent, and tradeoff versus the sibling. An agent has enough information to select and invoke the tool correctly without further inference.

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%, with every parameter already documented as an alias for the natural-language question. The description adds no additional parameter semantics beyond what the schema provides, so the 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 clearly identifies this as a hallucination-resistant answer mode for high-stakes reads, with specific verbs and a defined resource: extracting grounded answers from tool results. It also differentiates itself from sibling ask_pipeworx by emphasizing evidence-based extraction and refusal behavior.

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 says to use this tool when answers will be quoted, cited, or acted on and the agent must not invent facts, listing high-stakes domains. It also explicitly recommends preferring ask_pipeworx for casual lookups due to the extra LLM call, giving clear 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.