Start a screen recording on an Android device and save it as MP4 via ADB. Pair with the stop command to end the capture; Android limits each recording to roughly 180 seconds.
Start recording the screen to an mp4 on the device (Android caps a single recording at ~180s). Pair with stop_screen_record.
| Name | Required | Description | Default |
|---|---|---|---|
| serial | No | Target device serial (adb -s). Optional when exactly one device is attached. |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does reveal important behavioral traits: it records to an mp4, the recording auto-caps at ~180s, and it is meant to be paired with a stop command. This goes beyond a simple 'starts recording' and gives non-obvious constraints, though it stops short of detailing every side effect (e.g., storage, permissions, behavior if already recording, output location).
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 two concise sentences: the first states the action and output, the second adds a critical constraint and pairing instruction. Every word adds value—no filler, and the most important information (what it does) is front-loaded.
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 a single optional parameter and no output schema, the description is reasonably complete. It covers the core action, output format, system limitation, and the necessary companion tool. Minor omissions (e.g., where the file is saved, behavior if a recording is already active) could be added, but the essential context for correct invocation is present.
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 single parameter 'serial' has 100% schema description coverage with a clear explanation: 'Target device serial (adb -s). Optional when exactly one device is attached.' The tool description itself adds no parameter-level information, but since the schema already provides full coverage, the baseline score of 3 applies.
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 a specific verb ('Start recording') and resource ('screen to an mp4 on the device'), clearly distinguishing this tool from the sibling 'screenshot' (still image) and other capture tools. It also includes a concrete output format and a key constraint (Android ~180s cap), leaving no ambiguity about the tool's function.
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 clear context for usage: it starts a screen recording and explicitly instructs to pair with 'stop_screen_record' for termination. It also mentions the Android time limit, which serves as a usage boundary. While it does not explicitly list alternatives or exclusions, the pairing and format guidance effectively distinguish it from related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.