Phase 1 of 2 in the purchase flow. Convert a cart (or inline items + customer) into a checkout. Customer name, email, and phone are required. Returns checkout_id. No payment link is minted yet — call complete_checkout for that. Use update_checkout to correct customer details before finalising.
| Name | Required | Description | Default |
|---|---|---|---|
| items | No | ||
| cart_id | No | Either cart_id or items required | |
| customer | No | ||
| payment_method | No | Default 'yoco' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses the phase, that it returns checkout_id, and that it does not create a payment link, which is useful. However, it does not explain side effects (e.g., whether the cart is modified or invalidated), permissions, or error behavior.
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 three sentences, front-loaded with the core purpose, and each sentence adds distinct value: phase, required fields, and next steps. No filler or redundancy.
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 the tool's complexity (2-phase flow, nested customer object, two input modes), the description gives essential context: phase, required fields, and what it returns. It lacks details on error conditions and side effects, but covers the primary usage scenario well. The presence of sibling tools like complete_checkout and update_checkout fills some context gaps.
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 50%, so the description must compensate. It explains the either/or relationship between cart_id and items, and clarifies that customer name/email/phone are required. However, it does not detail the structure of the items array, which remains opaque.
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 function: converting a cart or inline items and customer into a checkout. It explicitly positions this as Phase 1 of a 2-phase purchase flow, distinguishing it from complete_checkout and update_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?
Provides clear guidance: use before complete_checkout, use update_checkout for corrections. It specifies required customer details and notes that no payment link is minted yet. It doesn't explicitly mention when to use create_cart or when to avoid this tool, but the phase context gives sufficient direction.
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 have clearly distinct purposes, but search_products and lookup_catalog overlap significantly in filtering by category and dimensions, which could confuse an agent. The three search/filter tools have subtle differences described, but the overlap lowers the score from perfect.
All tools use consistent snake_case with verb-noun structure (e.g., cancel_cart, get_product, update_checkout). There is no mixing of conventions, and the verbs clearly indicate the action, making the set predictable and easy to parse.
26 tools is slightly above the typical well-scoped range of 3-15, but the domain of an e-commerce blinds shop with additional services like AR, swatches, and price matches justifies the count. A couple of legacy tools (create_order, submit_enquiry) add minor bloat.
The core purchase flow (search, configure, cart, checkout, payment, order tracking) is fully covered. Additional services like AR visualization, swatches, price match, and WhatsApp handoff are present. Missing features like order listing or coupon application are minor gaps.