cursor_request_async

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

The description adds meaningful behavioral context beyond annotations: the request runs as a durable background job rather than blocking, and results are retrieved separately through the poll/collect pattern. Combined with the rich schema-level behavior (no output until exit, total-runtime timeout, yolo mode, rejection of mcp_managed), the agent gets a solid picture of how this tool behaves. No contradiction with annotations.

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?

Two sentences with zero waste. The first sentence front-loads the core action and durable-background nature, and the second gives the essential follow-up workflow. Every word earns its place.

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 tool with 22 parameters and complex provider-specific constraints, the description is quite complete because the schema carries the heavy parameter-level burden and the description covers the job lifecycle. It falls slightly short by not explicitly naming the synchronous cursor_request alternative or stating when to use the async form, but the 'durable background job' phrasing and poll/collect instructions make the core workflow clear.

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 100%, so the baseline of 3 applies. The tool description itself does not add parameter-specific semantics beyond the schema; the mention of poll and collect relates to job lifecycle rather than any input parameter. It neither worsens nor improves on the schema's already thorough parameter documentation.

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 states a specific verb and resource: 'Start a Cursor Agent CLI request as a durable background job.' This clearly distinguishes it from the synchronous cursor_request sibling and from other providers' async tools. It also signals the intended follow-up via llm_job_status and llm_job_result, making the purpose unambiguous.

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 clear usage context: this is a background job that should be polled with llm_job_status and collected with llm_job_result. However, it does not explicitly explain when to prefer this over the synchronous cursor_request or other async variants, so the guidance stops short of full when/not-to-use routing.

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