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

Annotations already cover readOnly, openWorld, idempotent, and non-destructive behavior. The description adds valuable context beyond that: it describes the internal routing and extraction process, the refusal mechanism with specific reasons (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), and the cost implication. While it doesn't elaborate on every aspect of the safety profile, the annotations cover those, so the description supplements rather than repeats.

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 and well-organized, front-loading the core purpose before detailing the response format, usage scenarios, and cost. Every sentence contributes to decision-making. It's slightly longer than minimal but justified by the complexity of the refusal logic and tradeoff with the sibling tool.

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?

Given the absence of an output schema, the description fully explains the return structure including success and refusal payloads, enumerates all refusal reasons, and clarifies when to use this tool versus the alternative. It also mentions the cost tradeoff, ensuring an agent has all necessary information to call it correctly in high-stakes contexts.

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 the question parameter and all five aliases fully documented. The description adds minimal value: it mentions the parameter is in natural language but doesn't provide syntax or formatting rules beyond what the schema already states. This is the baseline score for full schema coverage without additional semantic depth.

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, distinguishing it from ask_pipeworx by emphasizing that it extracts answers only from the tool result and returns evidence. It explicitly names the sibling it derives from (ask_pipeworx) and contrasts the two, leaving no ambiguity about its specific role.

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?

Provides explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' with concrete examples. It also gives a when-not-to-use: 'prefer ask_pipeworx for casual lookups' and explains the cost tradeoff, making the selection criteria crystal clear.

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