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

Annotations already declare the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), and the description adds substantial behavioral context on top: the exact success return shape (answer, evidence as verbatim quote, confidence, source, fetched_at), the exact refusal shape with all five refusal reasons enumerated, the guarantee that it extracts only from tool results, and the one-extra-LLM-call cost. This is the level of behavioral disclosure an agent needs to trust and act on the result.

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: identity, mechanism, success shape, refusal shape, usage policy, and cost tradeoff are each covered in one efficient clause or sentence. It is front-loaded with the key differentiator (hallucination-resistant) before any mechanics. Minor deduction only because the length is at the upper bound of what an agent can parse quickly.

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 compensates by documenting both the success and refusal return shapes, enumerating all refusal reasons, stating the extra-call cost, and naming the sibling to prefer for casual use. An agent has everything needed to decide to call it, invoke it correctly, and interpret any response — including the critical refusal cases where it must not fabricate an answer.

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 one required parameter (question) is fully documented with its five aliases (query, q, prompt, text, input) and a clear natural-language description. The tool description adds no parameter syntax details, but none are needed; the schema already carries the load. Baseline 3 is appropriate since the description's mention of "fills arguments" refers to internal routing behavior, not a user-facing parameter concern.

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, differentiating verb phrase — "Hallucination-resistant answer mode for high-stakes reads" — and precisely defines the tool's mechanism: route through 5,798 tools, fetch data, then extract the answer using ONLY the tool result. It explicitly names its sibling distinction ("Same routing as ask_pipeworx... Costs one extra LLM call vs ask_pipeworx"), making it unambiguous which tool this is versus ask_pipeworx and ask_pipeworx_beta.

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 with concrete domains: "Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements)." It also states the exclusion condition and preferred alternative: "prefer ask_pipeworx for casual lookups," including the cost rationale. Nothing about selection logic is left to inference.

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