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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so thoroughly. It explains side effects: subscription to the existing device control session, server-side remuxing, auto-stop behavior, lack of on-device storage or FLAG_SECURE limitations, and the single-recording-per-device rule.

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 detailed yet compact, with the core operation front-loaded. Each additional sentence earns its place by explaining critical behavioral constraints, output, or pairing with `device_record_stop`, with no redundant 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 two-parameter tool with no output schema, the description is complete: it specifies the return contract (`recordingId` for `device_record_stop`), auto-stop limits, concurrency restrictions, and the underlying session behavior. An agent has enough information to select and invoke this tool correctly.

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 schema already documents `udid` and `maxDurationSec` effectively. The description reinforces the default/max behavior of `maxDurationSec` but does not add meaning beyond what the schema already states, so the 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 states a specific verb and resource: 'Start a screen recording on an Android device.' It further distinguishes this from related flows by describing server-side remuxing, the shared device control session, and the `device_record_stop` pairing, so an agent can separate it from streaming or performance-recording 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?

The description gives clear context for when this tool is appropriate: when a screen recording should be saved server-side as an mp4, with no on-device storage and no built-in recorder limits. It contrasts with on-device recording behavior ('no 180 s on-device recorder cap') and notes the one-recording-per-device constraint, though it does not explicitly name sibling alternatives such as `android_video_stream` or `android_performance_record_start`.

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