watch.start

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

No annotations are provided, so the description carries the full burden. It discloses that the operation is asynchronous, returns immediately with a task ID, depends on a local HTTP service, and is followed up via watch.job. It does not cover error behavior or side effects, but the provided behavioral context is meaningful and non-redundant.

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 compact sentence with no filler. It front-loads the core action and return behavior, then adds the HTTP requirement and follow-up routing. Every clause contributes useful information.

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 async behavior, the dependency, and the follow-up query, but it leaves all four optional parameters undocumented. Since the input schema also has zero descriptions, the agent lacks enough detail to construct a correct invocation. The output schema exists, but the input side is severely under-specified.

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 0% for four parameters, and the description does not explain any of them. The agent cannot infer the meaning of all, limit, watch_id, or enrich_sellers from the text, making parameter selection essentially guesswork.

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 ('提交后台监控'), the immediate result (returns a task ID), and a key prerequisite (local HTTP service). It also points to watch.job for follow-up, which helps distinguish it from sibling tools, though it does not explicitly contrast with near-siblings like watch.run or watch.add.

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 an explicit usage prerequisite ('需本地 HTTP 服务') and tells the agent to use watch.job afterwards to query the task. This is clear operational context, but it does not state when this tool should not be used or how it relates to alternatives like watch.run or watch.add.

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