Start Flow (Async)

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

The description adds significant behavioral context beyond annotations, including returning a taskId, pause/resume behavior with MCA_FLOW_PAUSE_RESUME, error conditions for active sessions, and the ability to cancel mid-flow via cancel_task. No contradictions 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?

The description is concise and front-loaded with the main purpose. It efficiently covers key points without unnecessary fluff, though it could be slightly more streamlined.

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 with 8 parameters and nested objects, the description covers the return value (taskId), how to handle results (poll, get), and key behaviors. With an output schema present, it doesn't need to detail return fields, making it sufficiently complete for an agent.

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?

While schema coverage is 100%, the description adds meaning by explaining how params are forwarded as environment variables, how manifest defaults merge with caller params, and specific details like driverCooldownMs being iOS-only. This goes beyond the basic parameter descriptions.

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 clearly states 'Execute a named Maestro flow' with specifics about resolving YAML files and merging parameters. It distinguishes the tool from siblings like list_flows and cancel_task by focusing on execution and navigation to incremental changes.

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 provides a clear use case: 'navigate to the area of an incremental change before verifying it.' It mentions related tools for polling and getting results, but lacks explicit comparisons to other execution tools like run_feature_test or start_test, which would improve guidance.

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