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

Annotations already mark the tool as read-only and non-destructive, and the description goes further by disclosing exactly how it behaves: it extracts answers only from tool results, returns a detailed structured response with verbatim evidence, refuses explicitly when data is insufficient, and costs an extra LLM call. This gives the agent an unusually clear picture of side effects, failure modes, and limitations beyond what annotations alone provide.

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 front-loaded with the most important differentiator—'Hallucination-resistant answer mode'—and every subsequent sentence adds necessary context: routing behavior, return shape, refusal reasons, usage guidance, and cost trade-off. Despite its length, there is no filler; each element earns its place.

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 that there is no output schema, the description fully compensates by specifying the exact success return object and the exact refusal object with possible refusal_reason values. It also covers when to use the tool, how it compares to ask_pipeworx, and the extra-cost consideration, making the tool's end-to-end behavior complete for an agent to invoke correctly.

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?

The input schema already covers all parameters at 100% coverage, including the primary question field and all aliases, so the description is not required to repeat them. The description does not add parameter-specific meaning beyond describing the tool's internal routing and extraction behavior, which is appropriate but does not elevate the score above the baseline.

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, behavior-defining phrase—'Hallucination-resistant answer mode for high-stakes reads'—and clearly states what the tool does: routes like ask_pipeworx, fetches data, and extracts an answer using only tool results. It differentiates from the sibling ask_pipeworx by emphasizing grounded evidence and refusal behavior, so an agent can distinguish it 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 the tool: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts.' It also names the alternative, ask_pipeworx, and tells the agent to prefer it for casual lookups, giving both an inclusion and exclusion rule for tool selection.

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