save_tag

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

With no annotations, the description carries the behavioral burden. It discloses the HTTP method, upsert behavior, and that tag field has no snapshot data. It does not mention return values, error behavior, authentication needs, or that an update overwrites existing data.

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 dense but purposeful sentence: it front-loads the operation and endpoint, then gives the required payload details. No filler words are present, though the long clause structure slightly reduces skimmability.

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 mutation tool with no annotations and no output schema, the description covers the essential call requirements but leaves several operational unknowns: the exact shape of the server contract, expected response, and error cases. It is sufficient to make a plausible call but not fully self-contained.

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 only describes entity as '标签对象', so the description adds crucial meaning by naming required subfields and the 'no snapshot data' constraint. It also explains that remaining fields follow the server contract, which helps agents construct the payload despite the schema being an open object.

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 clearly states the action '新增或更新标签' (add or update tag), names the concrete POST endpoint, and defines the upsert semantics. It is immediately distinguishable from siblings like delete_tag and save_bill because the resource and verb are explicit.

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?

It explains when update occurs ('带主键为更新') versus insert, and specifies required fields ('至少携带 tagId/tagName 与 userId'). However, it does not explicitly mention when not to use this tool or name alternative tools such as delete_tag.

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