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

With no annotations, the description carries the full burden and does it well: it discloses that on hosted endpoints the call does not create a persistent task, and returns an honest_note instead of pretending. That is exactly the kind of non-obvious behavior an agent needs. It stops short of saying whether the stdio path is asynchronous, whether a task starts immediately, or what the handle looks like.

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?

Three sentences, front-loaded with the action and return value, then the critical environment caveat. The closing clause ('不假装能保存跨请求任务') restates the point already made, which is minor redundancy but not harmful.

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 biggest pitfall (no persistence on hosted) but omits the follow-up workflow: that the handle should be polled with get_task_status and cancelled with cancel_task, and what the returned handle or honest_note contains. With no output schema, those return-value gaps matter more.

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 coverage is 100%, with an enum on task_type and a nested args object, so the schema already documents both parameters. The description adds nothing about what the three task types mean or what shape args should take per type. Baseline 3 applies when the schema does the work.

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 a specific verb and resource ('启动长任务并返回任务句柄'), so the agent knows exactly what the tool does and what it returns. It differs from the related tools (get_task_status, cancel_task) in lifecycle role, though it never names them explicitly.

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 is unusually explicit about when the tool will not work: hosted Cloudflare Workers endpoints have no cross-request persistence, so the handles are only usable in the stdio npm package. It points to the alternative (stdio mode via roboparts-mcp-server), which is real routing guidance. It doesn't advise on choosing among the three task_type values or when to prefer the synchronous siblings like bom_compatibility_check.

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