colehaan_product_recommendations

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

No annotations are provided, so the description carries the behavioral disclosure burden. It does disclose the internal resolution of handle to Shopify product ID and the fixed server-side storefront, which helps the agent understand that the tool is scoped to colehaan.com. It does not mention whether recommendations include normalized product data fields, pagination, or whether the 'intent' parameter changes the output structure. For a read-only recommendation lookup, this is moderate transparency but not rich behavioral 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, all informative. The main action is front-loaded, the unique scoping details (Shopify resolution, fixed storefront) follow naturally, and there is no redundant repetition of schema field documentation. Every sentence earns its place.

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 and no annotations, the description only partially covers important context. It tells the agent the tool is scoped to Cole Haan and requires a handle, but it does not state what normalized recommended products look like, whether the return is a list with product fields, or how intent changes the result set. For a simple recommendations endpoint with clear parameter docs, this is adequate but leaves an agent to infer output shape.

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 has 100% description coverage for all three parameters, including allowed values for intent (related, complementary), default and max for limit, and required handle. The description adds value by clarifying the handle is a product route handle that gets resolved internally, which is not in the schema. It does not add detail on how intent affects results, but schema is sufficient.

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 clear action and resource: it lists Cole Haan product recommendations, normalized for one product handle, on the fixed Cole Haan storefront. It is distinct from sibling tools like colehaan_product and colehaan_products because it is specifically about recommendations for a given product handle. However, it does not explicitly name sibling alternatives or mention the 'intent' parameter's role in differentiating related vs complementary recommendations, which would further sharpen purpose.

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 the route handle is resolved to a Shopify product ID, implying the caller should supply a Cole Haan product handle. It also notes the storefront URL is fixed server-side, so the agent knows it cannot change the site. However, it does not give explicit when-to-use guidance versus other recommendation tools, nor does it state that handle should come from colehaan_product or colehaan_products. This is clear context but lacks explicit exclusions or alternative routing.

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