申请退单

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

The description adds meaningful behavioral context beyond the annotations: submission triggers manual review, refunds are not immediate, and duplicate applications are rejected. It also discloses backend eligibility restrictions. These traits are not inferable from readOnlyHint=false, openWorldHint=true, or idempotentHint=false, and there is no contradiction.

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?

One dense sentence front-loads the action and the manual-review consequence, then packs the backend restrictions into a compact, scannable list. There is 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?

Combined with the rich schema, which already explains the confirm_token two-step confirmation flow, the description covers purpose, eligibility, timing, and post-submission outcome. Nothing an agent needs to decide whether to invoke this tool is missing.

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 100%, so the schema already documents id, remark, product enum, and confirm_token in detail. The description adds no parameter-level meaning beyond referencing the static-residential product scope, so the baseline 3 is appropriate.

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 states a specific action ('申请退单' – apply for refund) targeting a static-residential subaccount, and clearly distinguishes this tool from sibling order/subaccount tools by its refund purpose and manual-review caveat. The verb and resource are unambiguous.

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 explicitly states when the tool can be used ('只能在下单后 1 天内申请') and lists disqualifying conditions: renewed subaccounts, ongoing bandwidth upgrade orders, invoiced consumption records, and duplicate applications. This gives an agent clear go/no-go criteria, and no refund-specific sibling tool exists to confuse it with.

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