撤单

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already provide destructiveHint=true and readOnlyHint=false, covering the mutating nature. The description states the action (cancel) and the scope (specified order) but does not disclose additional behavioral traits such as idempotency, failure conditions for already-filled orders, or whether the order is removed permanently. It adds marginal scope context beyond the annotations, warranting a median score.

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 one short sentence that front-loads the primary action and then adds the critical identifier-choice constraint. It avoids fluff, every clause earns its place, though it is terse rather than comprehensive.

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 tool has 3 parameters, no output schema, and only a sparse description. It communicates the core action and the key identifier constraint, but omits details such as when cancellation might fail, the need to specify symbol alongside the chosen ID, and any confirmation behavior. This is acceptable but not fully complete for an agent to understand all edge cases.

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 schema has 0% description coverage, so the description must clarify parameters. It does this effectively by stating "orderId 与 origClientOrderId 二选一" — indicating the two identifiers are mutually exclusive alternatives (pick one). This is essential information absent from the JSON schema, but it still does not explain the symbol parameter's role, which remains minimal.

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 begins with a specific verb+resource pair: "撤销指定订单" (cancel the specified order). The word "指定" (specified) directly distinguishes it from the sibling tool trading_cancel_all, which cancels all orders, so the agent knows which tool is relevant for a targeted cancellation.

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 implies usage: cancel one specific order identified by orderId or origClientOrderId. It does not explicitly state when to avoid this tool (e.g., when wanting to cancel all orders, use trading_cancel_all) nor mention any preconditions like the symbol being required. It provides a parameter-choice guideline but no broader usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.