delegate

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

Annotations already declare destructive/openWorld/non-idempotent, so the safety profile is covered. The description adds substantial non-obvious behavior: the call blocks until the turn is terminal, it encompasses tool work and sub-agent follow-up, concurrent calls on a running session are rejected, and the reply plus sessionId come back. It does not spell out that the agent may modify files, but the blocking and concurrency semantics are genuinely informative.

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?

Five tight sentences with zero filler, and the core blocking behavior plus return contract are front-loaded before the caveats. Every sentence carries a distinct, useful fact.

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?

With no output schema, the description correctly discloses the return shape (Cursor's reply and the reusable sessionId). Combined with full schema coverage, an agent has what it needs to invoke the tool. The one loose end is the unexplained 'You decide CONTINUE, COMPLETE, or BLOCKED', which is opaque without further context.

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% across all 9 parameters, so the schema already carries defaults, enums, and constraints. The description adds little parameter-level detail beyond noting the sessionId is meant for reuse, which the schema also states. Baseline 3 is appropriate.

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 names a specific action (send a prompt to Cursor Agent) and a specific resource/session model, and states the blocking contract: it waits until the Cursor turn is terminal, including tool work and sub-agent follow-up. It also distinguishes itself from the wrong approach ('Do not shell out to the agent binary'), so an agent can tell this apart from the sibling cancel/doctor tools without opening a 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?

Gives real usage context: omit sessionId to start a session, reuse the returned sessionId for follow-up, and a second call against a still-running session is rejected. It also steers away from shelling out to the agent binary. It stops short of explicitly comparing itself to the cancel and doctor siblings, so it is strong but not exhaustive.

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