add_to_cartBuild a ready-to-checkout cart and return a cart link. The shopper completes checkout and payment securely on the store. Pass one or more line items.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | Line items to add to the cart |
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | ||
| cart_url | Yes | ||
| checkout | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey non-read-only, idempotent, non-destructive behavior. The description adds valuable context beyond this: it returns a cart link and explicitly states that checkout and payment happen securely on the store, setting correct expectations about the tool's side effects and boundary.
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 short, purposeful sentences: the primary behavior, the security/checkout boundary, and the input requirement. No filler or repetition, and the main purpose is front-loaded.
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?
With one well-documented parameter, helpful annotations, and an output schema present, the description provides everything needed to invoke the tool correctly. It also clarifies where the tool's responsibility ends (checkout/payment), making the behavior complete.
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 schema already covers 100% of the parameter documentation, including details for product, variant, and quantity. The description adds only 'one or more line items,' which does not meaningfully extend what the schema already provides. Baseline 3 is appropriate.
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 uses a specific verb ('Build') and resource ('a ready-to-checkout cart'), and clearly states it returns a cart link. This distinguishes it from the catalog/search sibling tools, which are all about browsing or retrieving content, not cart construction.
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 gives clear context: pass one or more line items to build a cart, and the shopper completes checkout/payment on the store. It implies the tool is not for processing payments, but it does not explicitly name alternatives or state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are scoped to either products or articles, but there are overlapping pairs: check_inventory and get_product both return price and variant stock, and fetch and get_article both retrieve full-text content. search, search_products, and search_articles also share similar search intent, though their descriptions help clarify scope.
The set mixes verb+noun tools like list_products, get_article, and search_products with bare verbs like fetch and search, and noun-phrase tools like best_sellers, popular_content, related_products, and store_info. The naming is readable and partially patterned, but not consistently structured.
15 tools is at the upper end of the typical range, covering both a storefront and a publication plus sitewide search. The count is reasonable for the combined scope, though a few tools like check_inventory and get_product overlap enough that the set could be slightly tighter.
The gateway covers catalog browsing, product search, inventory, cart building, store policies, article search/retrieval, recent content, popular content, and general site search. Minor gaps include no paged listing of all articles beyond recent and no direct category-filtered product listing, but core workflows are well supported.