Write a real pending order into the shop and return its pay page. Needs a token, because it puts a row in the shop's books; for an ordinary purchase use start_checkout instead.
| Name | Required | Description | Default |
|---|---|---|---|
| No | optional, for the receipt | ||
| items | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description discloses side effect (writes a pending order) and need for authentication token. While annotations say destructiveHint=false (so not destructive), it's a write operation; description adds the crucial 'puts a row in the shop's books' context. Could mention that idempotency is not guaranteed, but annotations already say idempotentHint=false. Strong coverage of behavioral traits not in annotations.
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?
Two sentences, front-loaded with purpose, second sentence gives the critical side-effect guidance and alternative tool. Zero filler.
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?
Description covers purpose, side effect, token requirement, and alternative. No output schema, but return is a pay page URL - description implies that. Could be slightly more explicit about what 'pay page' returns, but close to 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?
Schema covers 50% of parameters (items required, email described) and description mentions 'token' without a schema parameter (likely contextual token). No extra parameter guidance beyond what schema provides. Not harmful, but doesn't add much beyond schema.
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?
Clear verb (create) + resource (payment link) + effect ('writes a real pending order', 'returns its pay page'). Distinct from start_checkout which is named as the alternative for ordinary purchases.
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?
Explicitly states when to use ('for an ordinary purchase use start_checkout instead') and warns about side effect (requires token because it writes to the books). No other guidance needed.
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.
Each tool has a clearly distinct purpose: checkout flows are separated into start_checkout (guest) and create_payment_link (token-based), product discovery has list/search/get, and order tracking, reviews, shop info, and analytics are each unique. No two tools could be easily confused.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., create_payment_link, list_products, get_order_status), with only shop_info and usage_report as minor noun-style exceptions but still clear and predictable. The naming style is uniform.
With 9 tools, the server is well-scoped for an e-commerce assistant. Each tool covers a distinct operation—browsing, searching, ordering, checkout, reviews, shop info, and analytics—without redundancy or bloat.
The tool set covers the full lifecycle for a shop assistant: product discovery, details, reviews, checkout initiation, order status, and even administrative usage reporting. No critical gaps exist—no required operations like updating orders or managing carts are missing for the intended use case.