save_reimbursement

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

With no annotations provided, the description carries the full disclosure burden. It does disclose meaningful behavioral traits: the create-or-update mutation semantics, that 'reimbursement 无快照数据' (reimbursement has no snapshot data), and that the payload must follow a server-side contract. However, it omits return values, auth prerequisites, and error behavior — information an agent needs to safely predict the outcome of a mutation.

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 dense sentences with no filler: the first front-loads the operation, endpoint, and upsert rule; the second covers payload requirements. Every clause earns its place, and the most important information (what the tool does) appears first.

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 description covers the essentials for invocation — payload shape and upsert semantics — which is critical given the effectively empty entity schema. However, with no annotations and no output schema, it leaves return-value behavior and error handling completely unspecified, so an agent cannot fully predict the result of the call or handle failure 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?

Although schema coverage is nominally 100%, the entity parameter is an open object (additionalProperties: {} with zero property definitions), so the schema itself conveys almost nothing about the payload structure. The description compensates by explicitly listing the fields to include (billId/remark/amount and userId) and warning that the object has no snapshot data — genuinely additive meaning beyond the 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?

The description opens with '新增或更新报销' (create or update reimbursement), a specific verb+resource pair, then reinforces it with the exact endpoint 'POST /reimbursement/addOrUpdateReimbursement' and the upsert rule ('带主键为更新'). This makes the tool's function unambiguous and clearly separates it from delete_reimbursement and the other save_* siblings that operate on different resources.

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 gives concrete usage conditions: the upsert rule ('带主键为更新' — including a primary key means update) tells an agent exactly how to invoke it for both create and update modes, and it specifies which payload fields to carry. It doesn't explicitly name alternative tools or state when not to use it, but the resource-specific semantics plus the upsert clarity provide solid invocation context.

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