Create a pre-checkout cart from catalog line items. A cart is a mutable scratchpad: it moves no money and holds no inventory, so it carries estimated (server-derived) totals and NO payment_handlers. Assemble it, then create_checkout(cart_id) to convert. REQUIRES IDENTITY on a signature-required Terminal.
| Name | Required | Description | Default |
|---|---|---|---|
| line_items | No | Items, each `{ item: { id }, quantity }`. Prices are catalog-derived, never yours. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility. It discloses key behavioral details: the cart 'moves no money', 'holds no inventory', has 'estimated (server-derived) totals', and 'NO payment_handlers'. It also states the authentication requirement: 'REQUIRES IDENTITY on a signature-required Terminal.' This is comprehensive.
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 concise and well-structured. It leads with the main action, then adds necessary behavioral and workflow context in a few sentences without redundancy or unnecessary detail.
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?
The description covers purpose, workflow, behavioral traits, and prerequisites. The only minor gap is that it does not explicitly state the return value (e.g., a cart object with an ID), though it implies via 'create_checkout(cart_id)' that a cart_id is returned.
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 has 100% coverage with descriptions for line_items, including the format and the note that prices are catalog-derived. The tool description does not add extra parameter-level semantics beyond what the schema already provides, so the baseline 3 applies.
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 states the tool's purpose with a specific verb and resource: 'Create a pre-checkout cart from catalog line items.' It also distinguishes itself from siblings like create_checkout by emphasizing the cart is a temporary scratchpad, not a final checkout.
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 provides explicit workflow guidance: 'Assemble it, then create_checkout(cart_id) to convert.' This tells the agent when to use this tool and how it fits with the checkout flow. It does not explicitly describe when not to use it, but the context is clear.
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 map to a distinct lifecycle step, and the detailed descriptions separate discovery, cart, checkout, payment, order, and wishlist concerns well. However, get_product and lookup_catalog are largely the same lookup by identifier, discover_products and search_catalog overlap across scope, and update_checkout is actually a read-only no-op.
The set overwhelmingly follows a verb_noun pattern: create_cart, get_checkout, cancel_checkout, complete_checkout, search_catalog. Minor deviations are the wishlist_* resource-first subgroup and the misleading update_checkout, which does not perform an update.
At 23 tools, this sits at the heavy end of the range, though the broad commerce lifecycle does justify substantial surface area. The count is inflated by redundant product lookup tools and a no-op update_checkout, so a more trimmed set in the low-to-mid teens would be healthier.
The server covers the full shopper lifecycle well: discovery, product lookup, cart, checkout, payment, order placement, order read, refunds, and wishlist. Gaps are minor and workable, such as update_checkout not actually supporting updates and no explicit order-cancellation path once a checkout is complete.
