cursor_launch

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

No annotations exist, so the description carries the full burden and does so well: it warns the call can take minutes, explains the 'unknown' status ambiguity and reconciliation strategy, and states that idempotency replays are safe and never duplicate. This is exactly the operational context an agent needs before calling a long-running launcher.

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?

Front-loaded with the core action, then organized by parameter group and finally by return/polling behavior, with no filler sentences. It is on the long side, but nearly every sentence carries a constraint or warning that an agent would otherwise get wrong.

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?

Despite having no output schema and no annotations, the description explains the return values (agent_id AND run_id) and the follow-up action required, plus failure-mode handling. Nothing essential for a correct first invocation is missing.

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% across 8 parameters, yet the description documents prompt content, repo_url format (GitHub https URL), starting_ref semantics (branch or SHA, omit for repo default, don't assume 'main'), model id sourcing, model_params shape ({key, value} dicts restricted to cursor_models options), mode values ('agent'/'plan'), and idempotency_key behavior. Only 'name' is unaddressed, which is a minor omission given the depth elsewhere.

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?

States a specific verb and resource ('Launch a Cursor cloud agent and enqueue its first run'), which precisely identifies this as the agent-creation entry point distinct from cursor_status, cursor_followup, and cursor_list mentioned elsewhere in the text.

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?

Gives explicit routing: repo-less launches are for research/reviews/writing, pass repo_url when the agent should write code, call cursor_models first for model ids, and poll cursor_status with the returned ids. It also names the recovery path (cursor_list, idempotency_key retry) when status is 'unknown', leaving little to inference.

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