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

Beyond the readOnlyHint annotation, the description discloses important behavior: duplicate seller listings are collapsed, hard filters exclude rows missing the attribute, soft preferences only re-rank without excluding rows, default sort is value, and price-dimension filters apply to live offer price in cents. It also notes that buy_url responses carry a disclosure field, which is substantive behavioral context not covered by annotations.

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 purpose and then layers in row contents, filter semantics, sort options, price filtering, and disclosure behavior. It is dense but mostly earns its length; the enumeration of row fields is slightly long but still useful for understanding the return shape.

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 complex 7-parameter tool with no output schema, the description covers the return shape, deduplication, hard versus soft filtering, sort behavior, and commission disclosure. It leaves pagination details such as cursor behavior and the limit maximum/default unspecified, which are minor gaps but relevant for correct invocation.

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 low at 29%, but the description compensates substantially by explaining sort options, hard versus soft filter semantics, Price-dimension min/max behavior, and preference examples such as 'Rated Noise, prefer low' and a pet-hair rating, prefer high. It does not explain cursor or limit behavior, leaving some parameter semantics undocumented.

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?

States a specific verb and resource: returns a category's consolidated, ranked shelf with duplicate seller listings collapsed. This clearly distinguishes it from sibling tools like search_products or find_category by describing the output as a deduplicated, ranked category shelf rather than a search or lookup.

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?

Usage is implied by 'Return a category's consolidated, ranked shelf' and by explaining hard filters versus soft preferences, but it never explicitly says when to use this tool instead of search_products, find_category, or get_products. The sort and filter semantics help an agent use the tool once selected, but tool selection guidance 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.