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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds substantial behavioral context: the refusal contract with exact refusal_reason values, the evidence/verbatim-quote return shape, the 'ONLY what the tool result contains' guarantee, and the extra LLM call cost. An agent knows this tool will refuse rather than invent.

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 efficient: purpose, return contract, usage rules, and cost tradeoff are covered in a few sentences, with the core behavioral guarantee front-loaded. The detail about refusal reasons is warranted and not filler.

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 one-parameter tool with no output schema, the description essentially supplies the output schema (success shape and refusal object with all refusal reasons), the hallucination-resistance guarantee, and the selection tradeoff against ask_pipeworx. Nothing needed to call it correctly appears missing.

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?

Parameter schema coverage is 100%, including all five aliases for the single required question parameter, so the schema already handles parameter meaning. The description adds no parameter-level detail beyond indicating natural-language questions, so the baseline 3 is appropriate.

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 names a specific mode ('hallucination-resistant answer mode'), a concrete workflow ('picks the right tool... fetches the data... EXTRACTS the answer using ONLY what the tool result contains'), and immediately contrasts it with ask_pipeworx. An agent can distinguish this grounded variant from the sibling list without opening 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?

States explicit usage conditions: use when an answer will be quoted, cited, or acted on and facts must not be invented, with example domains (financial verdicts, legal claims, medical lookups). It also gives the exclusion—prefer ask_pipeworx for casual lookups—and notes the extra LLM call cost, guiding tool selection.

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