cursor_launch

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

No annotations exist, so the description carries full disclosure and does so richly: launch can take minutes, a status of "unknown" may still mean the agent was created, and idempotency_key replays are safe and never duplicate. It also states the return contract (agent_id AND run_id) for polling.

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 grouped into prompt quality, repo vs repo-less, model selection, and return/failure handling. Multi-paragraph but each sentence carries a distinct operational instruction with no filler.

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 an 8-parameter mutation tool with no annotations and no output schema, the description covers invocation prerequisites (cursor_models first), return values (agent_id + run_id), and failure/reconciliation behavior (status "unknown", cursor_list, idempotent retry). Nothing an agent needs to call this correctly 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%, so the description must compensate and largely does: it explains prompt content, repo_url format (GitHub https URL), starting_ref (branch or SHA, defaults to repo default), model (id from cursor_models), model_params ({key,value} dicts restricted to cursor_models values), mode ("agent"/"plan"), and idempotency_key semantics. Only 'name' is left undocumented.

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+resource ('Launch a Cursor cloud agent and enqueue its first run'), immediately distinguishing it from lifecycle siblings like cursor_followup, cursor_status, and cursor_cancel. An agent can tell exactly what this does without opening the schema.

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?

Explicitly routes usage: repo-less launches are 'for research, reviews, and writing' while repo_url is for code-writing agents, and it instructs calling cursor_models first to obtain a verbatim model id. It also gives when-not guidance (never pass literal "Auto", omit model instead; never assume "main" for starting_ref).

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