replay

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

The description discloses one behavioral trait: session persistence when a script lacks a terminal close. However, it does not mention that replay executes automation on a device, which could have side effects like app state changes or network activity. With no annotations provided, the absence of warning about potential destructive or mutation behavior is a notable gap.

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 only two sentences, both relevant and packed with information about the core action and session behavior. It is well-structured and front-loads the verb 'Run', making it easy to scan. No unnecessary 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 a tool with 37 parameters and a rich output schema, the description is under-specified. It omits what a 'recorded automation script' is, how to point to it (though `path` is required), and any workflow for device selection or session initialization. The schema helps, but the description alone leaves the agent without enough high-level context to choose parameters intentionally.

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?

The input schema already provides descriptions for 76% of the 37 parameters, including selectors like `udid`, `platform`, and `device`. The description itself adds no parameter semantics; it references neither the `path` requirement nor any of the optional selectors. Since the schema covers most parameters adequately, a baseline score of 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 clearly states the primary function: 'Run a recorded automation script'. It adds specificity by mentioning 'compatible Maestro YAML flows', which gives the agent context about supported formats. However, it doesn't differentiate from sibling tools like `test` which might also execute scripts, so the purpose is clear but not uniquely positioned.

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 gives no guidance on when to use replay versus alternatives. It does not mention prerequisites, cooldowns, or scenarios where another tool (e.g., `record` or `test`) would be preferred. This is a significant gap for a tool with many sibling automation commands.

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