lululemon_product

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

With no annotations provided, the description takes full responsibility for transparency. It discloses the exact nature of the response (individual SKUs, prices, sale status, availability, rating, reviews), the input-derived 404 behavior ('An unrecognized product_id returns 404'), and clarifies that the slug is not needed. It doesn't mention authentication or rate limits, but for a simple read-only product detail fetch those are not obvious missing facts. The 'Get' verb itself communicates the read-only nature, and the 404 note adds useful edge-case behavior beyond 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 informative and front-loads the core action, then defines the specific content, parameter source, and error case. It is not overly long for the information conveyed. A small redundancy exists ('Full detail' appears in the first and second sentence), and the parameter section could be slightly tighter, but each sentence contributes substantive guidance, so it earns a 4.

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 there is no output schema, this description does a thorough job of describing the return values: per-color/per-size SKU prices, sale status, live availability, aggregate rating, and full reviews, including the caveat that ratings/reviews appear only if any exist. It also covers the input source, an example URL structure, and the failure mode. An agent has everything needed to decide when and how to call this 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?

Despite the schema having full coverage of the single product_id parameter, the description adds genuinely useful semantic detail not present in the schema: product_id can be sourced from a lululemon-category result's id OR the trailing path segment of a product URL, the slug can be omitted, and an unknown id returns 404. This helps an agent correctly extract the value from different contexts and reduces parsing ambiguity.

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 opens with a specific verb-resource pair ('Get a lululemon product's full detail') and immediately follows with a concrete enumeration of the returned content (per-SKU pricing, sale status, availability, ratings, reviews). It also explicitly differentiates this tool from lululemon-category, which only exposes a representative color/price. An agent can tell exactly what this tool does and how it differs from the sibling.

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?

It clearly states the alternative (lululemon-category), explains the gap that this tool fills ('none of which lululemon-category exposes'), and gives the practical implication: use this tool when full SKU/rating/review detail is needed. It also provides concrete guidance on where product_id comes from, including both the category-result id field and the URL path segment, and notes that the slug is irrelevant. This is explicit when-to-use guidance.

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