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

Beyond the safe readOnly/openWorld/idempotent annotations, the description discloses the refusal behavior with exact refusal reasons, the evidence-quoting guarantee, the exact success return shape, and the extra LLM call cost. It explains that the tool will not fabricate answers when data is incomplete, which is critical behavioral context for an agent deciding whether to trust the result. No contradiction with 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 long but every sentence earns its place: it fronts the most important property (hallucination resistance), then specifies the routing/behavior, return shape, refusal semantics, usage domain, and cost trade-off in a compact progression. It is organized as dense, scannable sentences rather than padding.

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 no output schema, the description fully specifies the success and failure return contracts, including refusal reason enums and the evidence field. It also covers the key selection decision versus ask_pipeworx and the operational cost implication. An agent has everything needed to invoke it correctly and interpret the result.

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 documents all six parameters at 100% coverage, and the description does not need to add parameter-level syntax. The description's behavior detail implicitly clarifies that the single required parameter is the natural-language question, but that is already in the schema. Baseline 3 is appropriate because the schema carries the full burden.

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 states a specific, differentiated purpose: a hallucination-resistant, grounded answer mode that routes through the same tool-selection pipeline as ask_pipeworx but extracts answers only from fetched tool results. It distinguishes itself from the sibling ask_pipeworx by naming the behavioral difference (grounded extraction + refusal on insufficient data). The verb 'EXTRACTS' and resource 'tool result' make the core operation unambiguous.

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 gives explicit when-to-use guidance: 'Use whenever an answer will be quoted, cited, or acted on' and lists concrete high-stakes domains. It also gives a clear when-not-to-use rule: 'prefer ask_pipeworx for casual lookups,' supported by the cost trade-off of an extra LLM call. No alternative is left unaddressed.

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