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

Goes well beyond the readOnly/idempotent/openWorld annotations by disclosing the full refusal contract: the success envelope {answer, evidence, confidence, source, fetched_at, refusal_reason:null} and the enumerated refusal reasons (not_in_source, no_tool_match, tool_error, data_truncated, llm_error). Also discloses the cost trait (extra LLM call vs. ask_pipeworx). Reading and fetching is consistent with readOnlyHint=true — no contradiction.

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?

Front-loaded with the key differentiator, then organized as mechanism → return contract → when-to-use → cost tradeoff. Every clause earns its place: the detailed return format is essential because no output schema exists, and the sibling comparison is essential because ask_pipeworx exists. Dense but not padded.

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?

Despite having no output schema, the description fully documents the return contract for both success and refusal paths, including all five refusal reasons. Annotations cover the safety profile, the schema covers the parameter, and the description covers behavior, cost, and applicability. Nothing an agent needs to invoke this tool correctly 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% — the single required parameter is fully documented as a natural-language question with five named aliases (query, q, prompt, text, input), so the schema carries the parameter burden. The description's high-stakes factual framing indirectly informs what to ask, but it adds no semantic detail about the parameter itself. Baseline 3 is appropriate.

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?

Opens with a specific, differentiating frame — "Hallucination-resistant answer mode for high-stakes reads" — and explains it extracts answers only from what the tool result contains. It distinguishes itself from sibling ask_pipeworx by the grounding behavior while acknowledging shared routing, so an agent can tell the two apart immediately. The verb+resource is clear: answer questions grounded in fetched data.

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?

Gives explicit when-to-use guidance: "Use whenever an answer will be quoted, cited, or acted on" with concrete high-stakes domains (financial verdicts, legal claims, medical lookups, public statements). Gives explicit when-not-to-use guidance: "prefer ask_pipeworx for casual lookups," backed by a cost rationale (one extra LLM call). No inference is required from the agent.

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