cvs_category

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

With no annotations, the description carries the full burden. It discloses behavioral traits such as pagination (one page per call, page parameter), normalization of products (specific fields), case-sensitive facet values, and the regional egress issue. It could be improved by explicitly stating that it is a read-only operation and that it does not support mutations, but the detail about error behavior adds value beyond the schema.

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 relatively long but is information-dense. It front-loads the main purpose and return value, then details path usage, page, sort, and regional constraints. While it could be more concise by trimming some redundant phrasing, every section adds essential usage context.

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?

Without an output schema, the description must explain return values, which it does thoroughly: product details, total count, facets. It covers pagination (page parameter), sorting (sort parameter), facet syntax, and error conditions. The tool's complexity (multiple path types, facet suffixes) requires the depth provided; nothing critical is missing for an agent to invoke it correctly.

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 input schema has 100% coverage and provides basic descriptions for page, path, and sort. The description significantly enhances meaning: it explains the format of the path (examples of top-level, subcategory, brand pages), how to append facet-filter suffixes in the site's URL shape, the default behavior of page and sort, and the fact that filter values are case-sensitive. This goes well beyond the schema, which only gives terse descriptions.

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 states the tool 'Browse a CVS OTC category page' and details what it returns: normalized products with title, brand, image, prices, flags; total result count; and facets. It distinguishes itself from siblings like cvs_search and cvs_product by focusing on category pages and the OTC catalog.

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 explicitly explains when to use this tool: to retrieve a single page of a category, subcategory, or brand page's product grid. It mentions that it covers only the non-prescription retail catalog, and that a request from an unsupported region returns an upstream error, which helps agents avoid misuse.

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