seller_products

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

No annotations were provided, so the description carries the full burden of behavioral disclosure. The description mentions 'paginate through' results, giving some hint of paging behavior, but it doesn't disclose rate limits, whether this is a read-only operation (though implied by 'get'), what happens on invalid seller_id, or how results are ordered by default. For a pagination-capable tool with no annotation coverage, key behavioral details like results-per-page limits or empty-seller edge cases are missing.

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 sentence with zero filler. It states the core purpose (get products) and a key feature (paginate through) with no wasted words. It's appropriately sized for the tool's complexity and front-loads both the action and the resource.

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?

This tool has 6 parameters, no annotations, and no output schema. It's moderately complex with pagination, field projection, marketplace selection, sorting, and language options. The description acknowledges pagination but doesn't set expectations for return values or result shape. However, given that the schema covers all parameters at 100% and the tool is functionality similar to a standard list-pagination pattern, the description is minimally adequate but could benefit from noting default behaviors and result limitations.

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%, so the schema documents all 6 parameters well. The description adds the notion of 'paginate through', aligning with the page and fields parameters. However, the description doesn't add much beyond what the parameter descriptions already state - it doesn't explain how fields projection affects response size, nor clarify interplay between sort_by, country, and language. Still, given full schema coverage, the baseline 3 is exceeded slightly because the pagination framing ties the parameters together coherently.

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 'Get and paginate through the products sold by an Amazon Seller' clearly states a specific verb (get/page through) and resource (products sold by an Amazon Seller). It distinguishes itself from sibling tools like product_search, best_sellers, deal_products, and seller_reviews, since it's specifically focused on a seller's products rather than general product lists or reviews. While clear, it doesn't explicitly contrast with seller_profile or products_by_category, leaving some ambiguity about edge delination.

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 implies usage (to retrieve a given seller's products) but provides no explicit guidance on when to use this vs alternatives like products_by_category or product_search. It names pagination as a capability but doesn't explain when pagination becomes necessary or how the fields projection interacts with data volume. There's no when-not-to-use guidance, and the sibling set includes closely related tools without explicit differentiation.

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