启动远程后台任务

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

The annotations already convey destructiveHint=true and readOnlyHint=false, so the agent knows it is a mutating operation. The description adds that the task is '可持续运行' (sustainable/long-running), but does not disclose other behavioral traits such as process persistence, output redirection, or cancellation behavior, which are relevant for such a tool.

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 that front-loads the core action and use cases. It is well-structured and efficient, though it could be expanded to include parameter guidance without harming conciseness.

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?

Given the tool has three parameters, a destructive hint, and no schema descriptions, the description is insufficient. It lacks essential information about parameter meanings, job lifecycle, and relationship to monitoring tools. The presence of an output schema lessens the need to describe return values, but operational context remains 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?

The input schema has 0% description coverage, and the description provides no explanation for any parameter (alias, label, command). The agent must infer their meaning solely from names, which is inadequate for correct invocation.

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 tool starts a remote background job (远程后台任务) and specifies common use cases (模型下载和推理). It distinguishes itself from siblings like ssh_job_status by the verb 'start' and the emphasis on long-running tasks, though it could be more explicit about the background aspect.

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 gives some usage context by stating it is suitable for model download and inference, implying long-running tasks. However, it does not explicitly compare with alternatives like ssh_execute for short-lived commands or mention when not to use this tool, leaving the relative decision to the agent.

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