sephora_category

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

With no annotations provided, the description partially carries the burden of behavioral disclosure. It explains the tool returns one page, uses Sephora's public catalog search as a fallback when legacy embedded data is absent, and keeps browse listings available. However, it doesn't disclose the underlying pagination behavior beyond page parameter, whether the response format matches the search tool's format, or any rate limits/quirks. The fallback mechanism is genuinely valuable context.

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?

Three sentences with dense, useful information. It front-loads the core function (Sephora category browse), explains the key parameter, and closes with an important behavioral note about the fallback mechanism. No filler words or redundant statements.

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 browse-listing tool with rich schema documentation (9 params, all described) and no output schema requirement, the description covers the essential context: what it does, how slug works, how filters relate to the sibling search tool, and key implementation detail about the catalog fallback. It doesn't detail the response structure, but given the schema covers all inputs and there's no output schema, this is acceptable.

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 baseline is 3, but the description meaningfully enriches the slug parameter by explaining its exact format and relationship to the URL structure. It also clarifies that the sort and facet filters behave the same as in /sephora/search, which adds semantic context beyond the raw schema definitions.

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 identifies the tool as a Sephora category browse tool, specifying it returns one page of category/browse listing (e.g., Makeup, Skincare) and provides concrete guidance on the slug format with an example. It meaningfully distinguishes itself from sephora_search by noting it supports the same sort/facet filters but is specifically for category pages.

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 the tool's context: browsing Sephora categories, with slug being the path segment after sephora.com/shop/. It references sephora_search for filter behavior, establishing a clear relationship. While it doesn't explicitly say 'use this instead of sephora_search when...', the category-specific focus and fallback behavior provide sufficient guidance for an agent to differentiate when to choose this tool.

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