tiffany_category

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It does disclose that the tool returns one page, that filters are single-value, and that empty or hub-level categories return a well-formed empty result. Nonetheless, it does not describe pagination methods (e.g., how to fetch additional pages), response structure, or any potential rate limits or auth requirements. These gaps are significant for a browsing tool with no output 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 composed of four dense sentences that front-load the primary purpose and then systematically cover parameter semantics and edge-case behavior. It avoids redundancy and conveys essential information efficiently, though it could be slightly more concise by removing some phrasing like 'category/browse listing'.

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 complexity (10 parameters, pagination, multiple filters) and lack of output schema, the description covers the core purpose and parameter sources but omits details about pagination semantics (e.g., how page and per_page interact) and what fields are returned per product. It also doesn't explain how to fetch subsequent pages. While it references supporting tools for filter values, the description is not fully complete for an agent to make advanced calls without additional inference.

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 already describes all 10 parameters with 100% coverage, so the description adds value by specifying that 'sort selects recommended (default), price_asc, price_desc, or newest', thereby indicating the default value. It also clarifies that filters are 'optional single-value filters' and that category IDs come from tiffany-categories, augmenting the schema's basic enum and reference 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's purpose: to 'Browse a Tiffany & Co. category' and returns 'one page of a Tiffany & Co. category/browse listing'. It identifies the resource (category) and the action (browse) precisely. It also names the sub-tools that provide the category IDs and filter values, distinguishing this from siblings like tiffany_search and tiffany_product.

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 explains that 'category is a category id from tiffany-categories's own id field' and instructs to 'see tiffany-filters for the live covered value space for each' filter, providing specific dependencies. It also states that invalid category IDs return empty results rather than errors, which guides expected behavior. However, it does not explicitly contrast this with alternative tools like tiffany_search or tiffany_product, so the guidance is not fully explicit about when not to use this tool.

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