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

The description is genuinely informative beyond the structured fields: it discloses the USDC charge per call, that spending is bounded by budget caps, and warns that results are third-party data rather than instructions (prompt-injection hygiene). However, 'each call is charged in USDC from the configured wallet' is a state-changing financial side effect that sits awkwardly against readOnlyHint=true, so the annotation and description are not mutually consistent. Score is above 1 only because the description is transparent about the conflict and the annotation is the misleading party; flagging remains warranted.

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?

Three tight sentences, front-loaded with the purpose before the payment model and the safety caveat. Every clause carries weight: routing, catalog pointer, cost model, budget bound, and injection warning.

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 an 80+-product dispatcher with no output schema, this covers the essentials an agent needs: how to find ids/params, that calls cost real money within caps, and that returned content is untrusted. It omits return-shape expectations and what happens when the budget cap is exceeded server-side (the confirm_over_cap flag only covers client behavior).

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 only 33%: 'params' (free-form object) and 'product' carry no description text, though the enum is largely self-documenting. The description partially compensates by telling the agent where to obtain valid ids and param shapes (list_products), and confirm_over_cap is fully documented in the schema itself. It does not explain the contents or nesting of 'params', so it only partly closes the coverage gap.

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 gives a specific verb+resource ('Buy any product by id') and immediately positions the tool as the fallback that applies 'when no other tool fits', which distinguishes it from the large family of specific siblings (market_quote, company_lookup, patent_lookup, etc.). Minor friction: the title says 'Call any product' while the description says 'Buy', so the exact nature of the operation (invoke a paid endpoint) is implied rather than stated crisply.

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?

Explicit routing rule — use this only when no other (more specific) tool fits — plus a concrete pointer to list_products for valid ids and param shapes. What is missing is any guidance on choosing among the 80+ product ids themselves, or on what to do if the required product is also covered by a dedicated sibling.

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