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

Annotations already declare readOnly/openWorld/idempotent, and the description is consistent with all of them. Beyond that, it discloses the full refusal contract with named reasons (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), the verbatim-evidence guarantee, and the one-extra-LLM-call cost — all behavior an agent cannot infer from the annotations or schema. Exceptionally transparent about limitations.

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?

Information-dense and front-loaded: the core differentiator (hallucination-resistant, grounded) lands in the first sentence, and each subsequent sentence adds a distinct fact — routing mechanism, success return shape, refusal return shape, use cases, cost tradeoff. Slightly long, but the refusal-reason enumeration and output contract justify the length given there is no output schema to carry that burden.

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?

No output schema exists, so the description correctly takes on the burden of specifying the return contract: {answer, evidence, confidence, source, fetched_at, refusal_reason} and the refusal variant with its five reasons. For a router over 5,798 tools with nuanced failure modes, this is nearly complete. Minor gaps: the semantics of the confidence field are undefined and no worked example question is provided.

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 `question` parameter is fully documented with its five aliases (query, q, prompt, text, input), so the schema carries the load. The description adds usage context about question type (high-stakes, factual, quotable) but no syntax or formatting detail beyond the schema. Baseline 3 applies under the high-coverage rule.

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 'Hallucination-resistant answer mode for high-stakes reads' — a specific mode, resource, and use case in one sentence. It names the sibling relationship ('Same routing as ask_pipeworx') and states the differentiator: 'EXTRACTS the answer using ONLY what the tool result contains.' This cleanly separates it from ask_pipeworx and ask_pipeworx_beta without needing to open either schema.

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?

Explicitly states when to use: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts,' with concrete example domains (financial verdicts, legal claims, medical lookups, public statements). It also gives the when-not and alternative: 'Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.' Both selection and exclusion criteria are explicit.

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