Skip to main content
Glama
rahulkr
by rahulkr

pull_recordings

Transfer screen recordings from Android devices to a local directory for analysis, testing, or backup purposes.

Instructions

Pull all screen recordings from device to local directory

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
local_dirNo./recordings
device_serialNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The main handler function for the 'pull_recordings' tool. It lists MP4 files in /sdcard/, pulls them using adb pull to the specified local directory, and returns the list of pulled files.
    @mcp.tool()
    def pull_recordings(
        local_dir: str = "./recordings",
        device_serial: str | None = None
    ) -> str:
        """Pull all screen recordings from device to local directory"""
        os.makedirs(local_dir, exist_ok=True)
        
        # List recordings
        files = run_adb(["shell", "ls", "/sdcard/*.mp4"], device_serial)
        if "No such file" in files or not files.strip():
            return "No recordings found on device"
        
        pulled = []
        for f in files.strip().split('\n'):
            f = f.strip()
            if f.endswith('.mp4'):
                local_path = os.path.join(local_dir, os.path.basename(f))
                run_adb(["pull", f, local_path], device_serial)
                pulled.append(local_path)
        
        return f"Pulled {len(pulled)} recordings to {local_dir}: {pulled}"
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. While 'pull' implies data transfer and 'all screen recordings' suggests bulk operation, it doesn't disclose important behaviors: whether this overwrites existing files, requires device connectivity, has timeouts, or handles errors. For a data transfer tool with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that communicates the core functionality without unnecessary words. It's front-loaded with the main action and follows a logical flow from source to destination. Every word serves a purpose in this compact formulation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (which handles return values), no annotations, and only 2 parameters, the description provides the minimum viable information about what the tool does. However, for a data transfer operation that could have significant side effects (file system changes, device connectivity requirements), the description lacks completeness regarding behavioral expectations and usage context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema provides no parameter documentation. The description mentions 'local directory' which corresponds to 'local_dir' parameter, and 'from device' which relates to 'device_serial', adding some semantic meaning. However, it doesn't explain parameter formats, optionality, or the implications of null device_serial. The description provides basic mapping but insufficient detail for confident parameter usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('pull') and target resource ('all screen recordings from device'), making the purpose understandable. It specifies 'to local directory' which adds useful context about the destination. However, it doesn't explicitly differentiate from sibling tools like 'pull_file' or 'screenshot_to_file', which might have overlapping functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'pull_file' or 'screenshot_to_file'. There's no mention of prerequisites, timing considerations, or when this tool would be preferred over other data retrieval methods. The agent must infer usage from context alone.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rahulkr/r_adb_mcp_server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server