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

Annotations only declare read-only/open-world/idempotent, but the description goes far beyond: it discloses the extractive constraint, the exact success payload, the full refusal taxonomy including data_truncated and llm_error with refusal_cause subcodes, and the added latency/cost of an extra model call. It does not contradict the annotations — the tool is a read, as declared.

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 differentiating claim and structured as behavior → return shapes → usage rule → cost caveat, with no filler sentences. It is dense and the parenthetical enumeration of refusal codes and refusal_cause values is heavy, but every clause carries information an agent needs.

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 fully by enumerating both the success object and every refusal shape with reasons. For a router-plus-LLM tool with 9 parameters, the description covers the routing behavior, failure modes, and cost that structured fields cannot express.

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% and the schema already documents the question aliases and prefer_tool's refusal behavior, so the schema carries the parameter burden. The description adds adjacent routing context (arguments are filled from the question, router picks among 7,181 tools) but never mentions aliases or prefer_tool directly, so it adds little parameter meaning beyond the structured fields.

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 function (grounded, extractive answering) and a specific mechanism: routing over 7,181 tools across 1,864 sources, then extracting only from the tool result. It explicitly contrasts with the sibling ask_pipeworx, so an agent can distinguish the two without inspecting either 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?

States a concrete when-to-use rule ('whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts') with example domains, and a when-not rule ('prefer ask_pipeworx for casual lookups') with the reason (one extra LLM call). Alternatives and the cost tradeoff are both named.

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