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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint), and the description adds materially more: fresh lists take 15-35 seconds, Amazon refreshes hourly so recent lists return instantly, and it is restricted to Amazon marketplaces. Latency/caching and domain-scope constraints are exactly the behavioral context annotations cannot express.

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?

Front-loaded with purpose, then mechanics, then latency, then alternatives — every sentence carries information and none is filler. It is one dense paragraph, though, and a slightly more scannable structure would help an agent parse the mode switch (url vs marketplace_id) at a glance.

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?

There is no output schema, and the description compensates fully by enumerating the returned fields (rank, ASIN, title, price, rating, ratings count, breadcrumb path, subcategory URLs) and the two operating modes. Nothing an agent needs to call 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%, so the schema alone sets a baseline of 3. The description adds genuine semantic value beyond it: the url parameter can be chained from a previous answer's subcategories/categories/path, and omitting url changes the call into a top-level category listing via marketplace_id. The pages semantics are only restated from the schema.

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?

Names a specific verb+resource ('Amazon Best Sellers list for one category') and immediately quantifies scope: up to 100 products in rank order with the exact fields returned, plus breadcrumb and subcategory URLs. It also states the second mode (marketplace_id only → top-level categories) and explicitly distinguishes itself from the keyword-search siblings.

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?

Gives the triggering user intent verbatim ('what sells best in a category right now', 'wants a top-100 list') and names the alternatives for the adjacent case ('For keyword searches use amazon_search_results or search_products'). It also explains the tree-walking procedure (root -> category -> subcategory, always reuse a URL from a previous answer), which is the non-obvious usage rule for this tool.

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