spawn_subagent

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

With no annotations, the description carries the transparency burden. It honestly explains the immediate return with a run_id, asynchronous execution, allowlist requirement, and how to observe progress. This provides strong behavioral context beyond a simple launch statement.

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?

Four short, purposeful sentences with no filler. The most important facts (launch, async, run_id) are front-loaded, and observation guidance is given next. Every sentence 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?

Given the tool's complexity (8 params, async behavior, no output schema), the description covers the key elements: what it does, return value, allowlist, and how to track progress. It doesn't detail every side effect, but it's sufficient for effective use alongside the schema and sibling tools.

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 parameters are well-documented elsewhere. The description adds only a small amount of extra meaning (e.g., prompt, allowlist) but mostly doesn't need to, hence the baseline score.

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 uses the specific verb 'Launch' with resource 'Cursor subagent' and 'give prompt', clearly stating the tool's core function. It also notes the asynchronous return of a run_id, which distinguishes it from sibling event/status/result tools.

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 implicitly establishes this as the tool to create subagents among siblings that manage them. It gives follow-up guidance ('Use get_subagent_events or subscribe...') and a precondition ('Model must be in the allowlist'), but lacks explicit 'when not to use' or alternative scenarios.

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