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

Annotations already mark the tool readOnly, idempotent, and non-destructive, and the description adds substantial behavior beyond that: result cap ('Returns up to 5 matching brands'), ordering ('best match first'), empty-result behavior, data freshness ('refreshed several times a day'), and a UI requirement ('Always show each store's links to the user'). This is rich, non-redundant context that meaningfully shapes how the agent presents results.

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 front-loaded with the core function and ranking logic, and every sentence earns its place — usage routing, return limits, freshness, and link display are all load-bearing. It is a long single paragraph, so a small deduction for scannability; breaking the usage-vs-alternative guidance into bullets would improve structure without adding words.

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 output schema exists, annotations carry the safety profile, and both parameters are fully documented in the schema, the description covers everything else an agent needs: sibling routing for retailer/category cases, ranking order, match cap, empty results, data recency, and required user-facing output. There are no missing behavioral or routing details.

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%; the schema already documents brand_name matching semantics and country_code format, defaults, and examples thoroughly. The description adds query examples ('Adidas', 'Apple') and implies brand_name is the central parameter, but does not need to compensate since the schema fully documents both parameters. 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 a specific verb and resource: 'Finds where to buy a brand's products with the most savings' and even specifies the ranking logic (cashback rate, then gift card discount). It explicitly names sibling tools it is not ('call get_cashback_rates_by_store_name instead; ... use get_best_deals_by_category'), so an agent can disambiguate without opening 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?

The description gives an explicit trigger condition ('Use it when the user names a product brand rather than a specific retailer'), concrete query examples ('where is the best cashback for Adidas products?'), and explicit when-not-to-use routing with named alternatives for both the retailer case and the product-type case. Nothing is left to inference.

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