preview_orderValidates price and stock before KFC China ordering, locks the current price, and returns a short-lived token for order placement; confirms totals, store, and login needs.
Server-side price/stock validation before ordering (locks the current price) and returns a previewToken for place_order. 结算预校验，返回金额、门店、是否需登录和 previewToken（10 分钟内有效）。
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does add useful behavior beyond the annotations: a 10-minute token TTL and the fact that the current price is locked. But "locks the current price" describes a server-side state change, which is at odds with readOnlyHint=true (no environment modification). The side effect is disclosed, but in a way that conflicts with the declared safety profile rather than clarifying it.
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 core purpose and the place_order handoff are front-loaded in the first clause, and the token TTL is attached where it matters. The Chinese sentence largely restates the first sentence before adding the return-field list, which is mild but real 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?
With no input schema to explain and no output schema available, the description compensates by naming the returned fields and the token validity window, which is the right shape for this tool. The one gap is that a price-lock side effect is never reconciled with the read-only annotation, leaving the agent unsure whether calling this mutates state.
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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The description correctly implies the tool derives its inputs from existing session/cart context instead of arguments, which is the only semantic question a zero-arg tool raises.
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?
States a specific verb and resource (pre-validate price and stock before ordering) and explicitly positions itself relative to a sibling by naming place_order as the consumer of the returned previewToken. It also enumerates what comes back (amount, store, whether login is required, token), so the agent knows exactly what this call yields without opening any schema.
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?
"before ordering" plus "returns a previewToken for place_order" gives a clear use condition and the downstream call it feeds. It does not name exclusions or say when to skip the preview (for example, when the cart is empty), so it stops short of full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.