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

Annotations carry the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial behavior beyond that: the internal routing mechanism across 5,798 tools / 1517 sources, the verbatim-evidence requirement, the structured return envelope, and an explicit refusal protocol with five named refusal reasons. It also discloses the extra-cost trait, which no annotation could express.

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 purpose, then flows logically through routing, return envelope, refusal contract, use cases, and cost tradeoff. It is dense, but every sentence contributes distinct information; the refusal_reason enum is the most expendable section, yet it is justified given there is no output schema to document it elsewhere.

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 single-parameter, fully-annotated, read-only tool with no output schema, the description is complete: return shape, refusal contract, sibling tradeoff, decision criteria, and cost behavior are all covered. An agent can select and invoke this tool correctly without additional lookups; at most one could wish for the confidence-value scale, which is minor.

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 fully documents the single required parameter 'question' along with its five aliases. The description does not add parameter-format details — the 'picks the right tool... fills arguments' line describes internal routing behavior rather than parameter semantics. The baseline 3 applies since the schema does the heavy lifting.

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.' It then names the closest sibling (ask_pipeworx) and explains the exact differentiator — same routing but extraction using ONLY what the tool result contains. This makes it immediately distinguishable from ask_pipeworx, ask_pipeworx_beta, and the other 27 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?

Provides explicit when-to-use criteria: 'whenever an answer will be quoted, cited, or acted on' with concrete high-stakes domains (financial verdicts, legal claims, medical lookups, public statements). It also gives the when-not-to-use case: 'prefer ask_pipeworx for casual lookups,' backed by a concrete cost rationale (one extra LLM call). Selection requires zero inference.

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