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

Annotations already carry readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is known. The description goes substantially beyond the annotations: it exposes the refusal behaviors and their exact reason enum (not_in_source, no_tool_match, tool_error, data_truncated, llm_error), the verbatim-quote evidence guarantee, the guaranteed refusal when data can't answer, and the extra-LLM-call cost. This is rich behavioral context, not a restatement of the 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 (~170 words) but genuinely information-dense: purpose, mechanism, success shape, refusal shape, use cases, and cost/alternative each appear once and nothing is repeated. It is front-loaded appropriately, though the prose block is a bit unwieldy; a short structured list for the return shapes would tighten it. Slight length penalty but all text 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?

For a tool with this much behavioral complexity and no output schema, the description fully compensates: it specifies the exact success return fields, the refusal payload, and the complete refusal_reason enum. Combined with guidance on when to prefer it and the added-cost warning, there is no missing information an agent needs to select and invoke this tool 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?

Schema description coverage is 100% — every one of the 6 parameters is documented in the schema, and 5 of them are self-explanatory aliases. The description adds 'Your question... Accepts... as aliases' which the schema already states, so its marginal value over the structured data is neutral. Baseline 3 applies: with perfect schema coverage, the description needn't carry the param documentation 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?

Opens with a specific, distinctive purpose: 'Hallucination-resistant answer mode for high-stakes reads.' It explicitly differentiates itself from the sibling ask_pipeworx by explaining the difference in mechanism ('EXTRACTS the answer using ONLY what the tool result contains') and by naming the sibling it is NOT ('Same routing as ask_pipeworx... prefer ask_pipeworx for casual lookups'). An agent can tell this apart from all 36 siblings without opening any schemas.

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?

Provides explicit when-to-use guidance with concrete domains ('financial verdicts, legal claims, medical lookups, public statements') and has explicit when-not-to-use guidance with the named alternative ('Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups'). Nothing is left to inference; the trade-off is fully disclosed.

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