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

Annotations are sparse (only readOnlyHint, openWorldHint, destructiveHint), so the description carries the burden. It discloses output composition, ordering, fidelity ('never paraphrased, never summarised'), the guarantee that it always contains what clinic_clinical_passage gives, the 'general information, not medical advice' caveat, and the exact price and payment rail. No contradiction with annotations.

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 purpose is front-loaded and every clause contributes either differentiation, fidelity guarantees, or cost/payment context. It is longer than strictly needed because of the full author credentials and payment clauses, but none of it is 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?

With no output schema, the description compensates well by explaining what the return contains (sections in order, matched passage, references, disclaimer) and its exactness guarantees. It does not describe the article title or metadata fields, but for a prose-return tool this is sufficient guidance for invocation.

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%, and the query parameter already has a thorough explanation of phrasing, deterministic keyword matching, and decline behavior. The tool description adds the use-case framing ('Need your answer in the prose it came from?') but does not materially extend the parameter semantics beyond the schema, so 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 opens with 'Clinical reference — one section' and immediately states the deliverable: the full article body in source order, the matched passage, references, and disclaimer. It also names the sibling tool (clinic_clinical_passage) and explicitly distinguishes the superset relationship, so an agent knows exactly what this tool returns and how it differs from nearby tools.

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?

It gives an explicit decision rule: use clinic_clinical_passage instead when the passage alone suffices, at a tenth of the cost, and warns that when the best match is itself a section this rung returns the same text, so the cheaper sibling should be bought. This goes beyond implied usage to tell the agent when not to invoke this tool.

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