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

Annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) are thin, but the description adds substantial behavioral context: the $1.00 USDC on Base via x402 cost, the verbatim delivery guarantee ('Never paraphrased, never summarised'), the non-medical-advice disclaimer, and the deterministic no-match decline behavior. This is exactly the kind of context an agent needs for a paid, open-world retrieval tool.

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?

Well front-loaded: opens with the core purpose and the central user question, then the alternative, then constraints. The author credential string (~25 words) is defensible for a clinical reference but slightly long, and the 'ladder' metaphor is evocative but assumes shared context with sibling definitions. Otherwise every sentence earns its place.

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 by enumerating the return contents (quick answer, sections, FAQs, citations, disclaimers) and the verbatim guarantee. The payment flow, decline behavior, and cost are all covered across description and schema. The only gaps are the exact response envelope format and the meaning of 'the ladder,' which are minor for a text-retrieval tool.

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% — both query and paymentHeader already have detailed descriptions covering GLP-1 topic scope, deterministic keyword matching, no-match decline behavior, and the 402 payment challenge flow. The tool description adds only marginal param insight (that the query selects the matched article and that output quantity is the sole differentiator vs the section tool). Baseline 3 is appropriate 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 states a specific action and resource: return the complete clinical article (quick answer, every section, FAQ, citation, disclaimer) matching the query. It explicitly distinguishes itself from clinic_clinical_section by defining the only difference as quantity ('The most text on the ladder and the same text; quantity is the only difference'), so an agent can disambiguate without opening other tool definitions.

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 framing ('Need the whole article, not only the part that matched?') and names the exact alternative with the selection condition: 'USE clinic_clinical_section INSTEAD if the article's body plus your match is enough, at a tenth of this.' The cost differential further informs the decision. No inference is required.

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