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

Annotations already establish readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, so the bar is lower. The description adds valuable behavioral context beyond annotations: it details the refusal mechanism (refusal_reason values like not_in_source, tool_error, data_truncated), the evidence-verbatim-quote output, and the extra LLM call cost — all behaviors an agent needs to predict side effects and failure modes.

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 front-loaded with purpose and every sentence earns its place: purpose, routing behavior, extraction mechanism, return/refusal shape, usage conditions, and cost trade-off. It is dense but not padded; the only mild over-specification is the parenthetical list of example high-stakes domains, which is brief and illustrative rather than redundant.

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 lacking an output schema, the description compensates by fully specifying the return shape ({answer, evidence, confidence, source, fetched_at, refusal_reason}) and the refusal enum, so an agent can anticipate both success and failure outputs. Combined with explicit usage guidance and cost awareness, the tool is operationally well-described for its complexity level.

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% — all six parameters (question plus five aliases q, text, input, query, prompt) are described, with each alias explicitly labeled 'Alias for question.' The description adds no further parameter nuance, but with full schema coverage the baseline of 3 applies.

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 purpose — 'Hallucination-resistant answer mode for high-stakes reads' — and uses a clear verb ('EXTRACTS the answer') tied to a distinct resource behavior. It explicitly differentiates from the sibling ask_pipeworx by emphasizing evidence-cited, source-grounded answers versus casual lookups, making the tool's role 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?

Usage guidance is explicit and actionable: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' directly states when to choose this tool. It also gives the negative case — 'prefer ask_pipeworx for casual lookups' — and explains the trade-off ('Costs one extra LLM call'), leaving no ambiguity about selection.

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