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

Annotations already mark readOnly, openWorld, idempotent, and non-destructive, but the description goes well beyond them by disclosing that answers are extracted only from tool results, that a refusal is explicit with enumerated refusal_reason values, and that an extra LLM call is incurred. This is rich behavioral context that materially affects how the agent should invoke and interpret the tool.

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 longer than average, but every sentence earns its place: core behavior, return contract, refusal semantics, usage guidance, and cost trade-off against the sibling. It is front-loaded with the most decision-relevant phrase ('Hallucination-resistant answer mode for high-stakes reads') and uses dashes to keep the structure scannable.

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?

With no output schema, the description fully specifies the success and failure return contracts, including field names and refusal reason enum values. It also explains the routing behavior, the cost implication, and the exact conditions under which the tool should be preferred. An agent has everything it needs to call and interpret 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 coverage is 100%; the schema already documents all six parameters as aliases for a natural-language question. The description adds no further parameter-level semantics, only reinforcing the internal routing behavior. Baseline 3 is appropriate because the schema fully carries the parameter 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?

The description clearly identifies this as a hallucination-resistant answer mode for high-stakes reads, explicitly distinguishing it from ask_pipeworx by the grounded extraction and refusal behavior. It specifies the exact return contract and refusal reasons, so an agent can tell exactly what this tool does and how it differs from siblings.

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 explicitly states when to use this tool ('whenever an answer will be quoted, cited, or acted on... must not invent facts'), gives concrete domains (financial verdicts, legal claims, medical lookups, public statements), and names the alternative (ask_pipeworx for casual lookups) with a cost-based rationale. This gives the agent clear decision criteria.

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