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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so safety is well covered. The description adds scope information (one product vs whole shop) but does not elaborate on pagination, sorting, or whether empty/missing review data is handled.

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 description is a single concise sentence with no fluff. Every word contributes meaning, and the main distinction—single product vs whole shop—is front-loaded.

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?

Given the tool's simplicity, one optional parameter, and rich safety annotations, the description is largely complete for purpose and selection. However, since there is no output schema, a bit more detail about what the returned reviews contain (text, rating, timestamps) would improve it.

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?

The schema only labels the slug as 'optional', but the description clarifies that it effectively 'scopes the query to one product, otherwise returns the whole shop'. This adds real meaning to the only parameter, going beyond the schema description.

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 clearly identifies the resource as customer reviews and communicates the retrieval scope: by product or across the whole shop. This distinguishes get_reviews from sibling tools like get_product, list_products, get_order_status, and create_payment_link.

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?

The phrase 'for one product or the whole shop' provides clear context for how the tool is used: optionally target a product via slug, or omit it for shop-wide reviews. It does not explicitly list exclusions or name alternative tools, but the usage context is clear.

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