归还图书

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

Annotations already declare idempotentHint=true and destructiveHint=false, and the description restates idempotency ('重复调用结果不变') without adding new behavioral context such as side effects on book availability, permissions required, or error behavior. The description does not contradict annotations, but it also does not enrich the safety profile beyond what structured data provides.

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 a single, concise sentence with no filler. It front-loads the core action ('根据借阅单归还图书') and appends the idempotency note, which is directly relevant. Every word contributes meaning.

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?

For a simple one-parameter tool with output schema and annotations covering idempotency and non-destructiveness, the description is mostly sufficient. It lacks explicit mention of error cases or prerequisites (e.g., loan must exist and be active), but the simplicity of the tool and the supporting structured data make it reasonably complete.

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 provides only the bare parameter name loan_id with no description, and schema description coverage is 0%. The description's '借阅单' (loan slip) gives a hint that loan_id references a loan slip, adding a small amount of meaning beyond the schema. However, it does not explain the format, where to obtain it, or how it relates to the returned book, leaving the agent partially in the dark.

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 uses a specific verb (归还/return) and resource (图书/book), and clarifies the basis (借阅单/loan slip). It clearly distinguishes itself from sibling tools like checkout_book by representing the inverse operation, and from search_books and audit_inventory which do not mutate loans.

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?

Usage context is implied: a book is returned after being checked out, using the loan slip. However, there is no explicit guidance about when to use this tool versus alternatives, nor any mention of prerequisites such as the loan being active or already returned. The route to the right tool is obvious from the name and description but not spelled out.

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