sevennow_category

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

With no annotations provided, the description carries the full burden. It discloses several important behaviors: the response includes a category-wide availability summary, pagination is applied uniformly to every subcategory group, and an invalid or empty category_id returns a normal 200 with an empty subcategories array rather than an error. It also explains the dual id-space behavior of category_id. The only minor gap is that it doesn't explicitly state whether the operation is read-only, but the verb 'Browse' and the absence of any mutation language make that clear enough.

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 dense but well-organized. It front-loads the core purpose, then adds the contrast with the sibling, then the parameter provenance, then the edge-case behavior. Every sentence earns its place, though it is slightly long and could be tightened. The structure is logical: what → how it differs → where inputs come from → what happens on invalid input.

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?

Given the tool's moderate complexity (5 params, no output schema, no annotations), the description covers the essential context: what the response contains, how it differs from the sibling, where the IDs come from, the dual id-space quirk, pagination behavior, and the empty-result edge case. The only thing missing is a more explicit statement of the return shape (e.g., that subcategories is an array of objects with name, items, etc.), but the description already mentions subcategories[].name and the availability summary, which gives a good picture.

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 already documents all five parameters. The description adds value beyond the schema by explaining the relationship between category_id and the two id spaces (departments vs merchandising shelves), and by clarifying that skip/limit apply uniformly to every subcategory group. It also explains that subcategory restricts by exact name from a prior call's subcategories[].name, which is already in the schema but reinforced. The description doesn't add much for store_id, but the schema already says where it comes from.

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 states a specific verb ('Browse'), a specific resource ('one 7NOW store's category'), and the key differentiator: it returns the category broken into real subcategory groups with paginated, priced item lists and live availability. It also explicitly contrasts itself with GET /7now/catalog, which returns a single flat list, making the distinction from sibling tools clear.

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 says when to use this tool vs the alternative: it 'Complements GET /7now/catalog, whose per-category section is a single flat list -- this is the same data organized the way 7now.com's own category page groups it.' This gives the agent a clear decision rule. It also explains where store_id and category_id come from, and notes that category_id accepts two id spaces (departments and merchandising shelves), which is essential usage guidance.

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