Create a new Agent Checkout-attributed cart with a selected product variant. Use only after the user has chosen a specific product or clearly asked to add/buy it. This prepares the purchase but does not charge the buyer.
| Name | Required | Description | Default |
|---|---|---|---|
| quantity | No | ||
| site_slug | Yes | ||
| variant_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present, the description carries the transparency burden and usefully discloses that this 'prepares the purchase but does not charge the buyer.' It also notes the cart is Agent Checkout-attributed, which is non-obvious context. It could clarify effects on an existing cart or required auth state, but the no-charge disclosure is meaningful.
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 sentences, with the core action front-loaded and each sentence adding a distinct fact: what it creates, when to call it, and what it does not do. There is no filler or repetition.
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 mutation tool with no annotations, no output schema, and zero schema description coverage, this is incomplete: site_slug and quantity semantics are missing, existing-cart behavior is unaddressed, and it does not indicate whether a cart identifier is returned for later create_checkout calls. It captures the high-level flow but leaves key operational details unspecified.
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 0%, so the description needed to compensate for all parameters. It only loosely maps to variant_id via 'selected product variant' and says nothing about site_slug or quantity. An agent would still have to infer the purpose of two parameters from their names and constraints.
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 gives a specific verb ('Create'), resource ('Agent Checkout-attributed cart'), and scope ('with a selected product variant'). It clearly separates this from retrieval or checkout-finalization tools by framing it as a new-cart preparation step.
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 explicitly states the precondition: 'Use only after the user has chosen a specific product or clearly asked to add/buy it.' This provides strong when-not-to-use guidance. It does not name sibling alternatives like add_to_cart or create_checkout, but it still gives a clear operational trigger.
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 target distinct steps in the purchase flow, and descriptions clarify the intended sequence. The main overlap is search_catalog being a legacy alias for search_products; check_inventory and get_product have slight overlap but are distinguished by availability checking versus detailed product info.
All tool names follow a consistent verb_noun snake_case pattern such as search_products, get_product, create_cart, add_to_cart, and create_checkout. The naming pattern makes the workflow stage and action immediately clear.
With 8 tools, the surface is well-scoped for a shopping-and-checkout flow: discovery, product details, inventory, cart creation/modification, cart review, and checkout handoff. The redundant search_catalog alias is minor and does not make the set feel bloated.
The core path is complete: search → product details → inventory check → create cart → add to cart → get cart → create checkout. Minor gaps such as removing or updating cart items are missing, but the essential purchase workflow is fully supported.