quince_product_reviews

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

With zero annotations, the description carries the full burden and delivers: it discloses the sample-only nature, the empirically confirmed 25-review ceiling, the non-paginated behavior, and the well-formed empty result for products with no reviews. This is exactly the behavioral context an agent needs beyond what the schema alone provides.

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 sentences, all value-dense and front-loaded with the core purpose and return shape. The final sentence packs the sample count, non-pagination, and empty-result behavior into one slightly dense clause, but nothing is wasted and the structure reads naturally.

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 read tool with no output schema and no annotations, the description covers the return payload, the sample limitation, the empty-result edge case, and parameter sourcing. Nothing an agent needs to invoke it correctly is missing.

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% — the schema already documents that handle is a product URL handle sourced from a search result's products[].handle field. The description adds only a cross-reference that the same value works for quince-product, which is marginal value beyond the schema. 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?

Opens with a specific verb + resource ('Get Quince product reviews') and enumerates exactly what is returned: normalized reviews (author, date, rating, review body), the aggregate rating, and review count. This clearly distinguishes it from siblings like quince_product and quince_product_faq without needing to open their schemas.

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 clear context on scope — it returns a fixed sample (~25 reviews), not a paginated feed of the full review history — so an agent knows this tool is insufficient for exhaustive review analysis. It stops short of naming an explicit alternative tool for the full review history, but the 'handle is the same value quince-product accepts' cross-reference hints at the related product tool.

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