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

Annotations already declare idempotentHint=true and destructiveHint=false, and the description is consistent with them by explicitly stating it does not create orders or refunds (不创建订单或退款). Beyond that, it discloses genuinely useful behavior: PAID only means payment, completed=true means entitlement issued, and a missing record must not be read as a failed deduction. This adds real context the annotations do not carry.

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?

Compact and front-loaded: login prerequisite first, then the verification action, then the PAID/completed semantics and the do-not-repay guardrail. Every clause carries meaning, though the terse '登录;' opening is slightly cryptic.

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?

No output schema exists, and the description compensates by explaining the key return fields (PAID, completed) and how to interpret a missing result. For a single-parameter read tool this is nearly complete; it does not cover whether multiple orders could match or what other fields are returned.

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 coverage is 0%, so the bare outTradeNo parameter carries no documentation. The description partially compensates by identifying it as the order number (订单号), but gives no format, length, or lookup-failure guidance specific to the parameter. With one parameter this is near the baseline.

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: verify (核验) the caller's own payment and invoice result by order number, back to source (回源). This clearly distinguishes it from create_payment_order, cancel_payment_order, and resume_payment_order, though those alternatives are never named. Purpose is unambiguous but sibling differentiation is only implicit.

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?

Gives concrete when/what-to-do guidance: if entitlement is not issued, keep checking or contact staff, and do not pay again (勿再付款); if nothing is found, do not conclude the deduction failed. It also states the login prerequisite. It stops short of naming the resume/create sibling tools to use in those edge cases.

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