oldnavy_category

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

With no annotations present, the description carries full behavioral burden and it does well: it discloses that cid is opaque, that no API-complete category-id list exists 'for now' (a change/fragility note), and that results are normalized product summaries with per-color inventory and live facet counts. It stops short of covering error behavior, auth, rate limits, and pagination details.

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?

Four sentences, each earning its place: core action first, then the cid-provenance constraint, then the brand parameter mapping, then the return payload. No padding or repeated schema content; the guidance is front-loaded so the agent gets the essential behavior in the first sentence.

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?

Because no input schema exists, the description compensates by naming the outputs (subcategory breakdown, normalized product summaries, per-color inventory, live facet counts), which is enough for an agent to judge whether to call it. The gaps — error behavior on mismatched brand/cid, pagination specifics beyond 'one-based', and whether products pages link back — would be nice but are minor for a browse tool.

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 already covers all three params, so the baseline is 3, but the description adds real value: it explains that cid is an opaque Gap Inc id sourced from a browse-page URL, and it enumerates the brand codes (`on`, `gap`, `br`, `at`) with the default and the match-must constraint — all absent from the schema's minimal property text for `brand`.

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?

Opens with a specific verb and resource: "Browse an Old Navy, Gap, Banana Republic, or Athleta category." It then states exactly what is returned (subcategory breakdown, normalized product summaries, per-color inventory, facets) and names the core input (cid), so an agent can tell it apart from sibling tools like oldnavy_search, oldnavy_categories, and oldnavy_product without opening their 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 concrete sourcing guidance: oldnavy-search and the category tool do not list category ids, so the agent must pull cid from the storefront's /browse/... page URLs, and it warns that brand must match the brand the cid was found under. It does not explicitly state when to prefer this tool over the search or product-detail siblings, so the when-to-use decision is mostly implied.

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