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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds substantial context beyond them: the full success payload, the five refusal_reason values, the refusal_cause subcodes for llm_error, and the one-extra-LLM-call cost. It does not discuss latency, rate limits, or how partial truncation is detected, which keeps it out of the top band.

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?

Front-loaded with the core distinction and the use case, with return shape and refusal codes following in a logical order. It is dense but nearly every clause carries information; the parenthetical breakdown of refusal_cause values is the one section that could be tightened without losing selecting power.

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?

There is no output schema, and the description compensates by specifying the exact success object and every refusal shape, including nested refusal_cause semantics. For a tool whose failure modes are the main selection risk, nothing an agent needs is 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?

Schema description coverage is 100%, so the required question field and its seven aliases are fully documented in the schema itself, and the baseline of 3 applies. The description adds routing context ('picks the right tool... fills arguments') that implies how the free-text question is consumed, but it never mentions prefer_tool or that it accepts tool names from alternatives[], which is the one non-obvious parameter here.

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?

States a specific verb+resource: grounded answer mode that routes to one of 7,176 tools, fetches data, and extracts the answer strictly from the tool result. It explicitly distinguishes itself from the sibling ask_pipeworx ('costs one extra LLM call... prefer ask_pipeworx for casual lookups'), so an agent can choose between them without opening a 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?

Gives an explicit trigger ('use whenever an answer will be quoted, cited, or acted on') with concrete examples (financial verdicts, legal claims, medical lookups), plus an explicit when-not ('prefer ask_pipeworx for casual lookups'), and names the cost tradeoff that drives the decision.

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