Skip to main content
Glama

Create Android device

device_create

AkaPhone: boot a fresh cloud Android 14 phone you can then screenshot, control and run tasks on. With wait (default) the call returns once the device is running, or after at most 25 s if it is still booting or capacity is busy (then it is still queued/creating; check again with device_list). Devices bill 1 credit per started minute while running and stop (saving their data) after 30 idle minutes; stop them with device_terminate when done and resume later with device_start.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "device_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoOptional friendly name
waitNoWait until booted, up to 25 s (recommended)
profileNoScreen profile id from profiles_list (default pixel_8)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided the description carries the full burden and does so: billing rate (1 credit per started minute while running), the 30-minute idle auto-stop that preserves data, and the wait-timeout behavior including the ambiguous queued/creating state and how to resolve it. This is exactly the cost and lifecycle context an agent needs before a billable mutation.

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

Conciseness4/5

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

Front-loaded with the purpose and then dense with cost and lifecycle facts; every clause carries information. It runs long as a single compound sentence with parentheticals, which costs a little readability, but nothing is padding.

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

Completeness5/5

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

No output schema exists, and the description compensates by describing exactly what the call returns (a booted device, or a queued state needing a device_list recheck). Cost model, idle shutdown and termination/resume path are all covered, so an agent can call this correctly and safely without opening anything else.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline would be 3; the description earns above that by explaining what wait actually does operationally (returns once running, or after at most 25 s, possibly still queued) and by naming the default profile behavior. The name parameter gets no mention, but it is a trivial optional field already documented.

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

Purpose5/5

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

States a specific verb and resource ("boot a fresh cloud Android 14 phone") and enumerates what the resulting device enables (screenshot, control, run tasks). The word "fresh" implicitly separates it from device_start, which resumes an existing device, so an agent can distinguish it among the siblings.

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

Usage Guidelines5/5

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

Explicitly routes the lifecycle: stop with device_terminate when done, resume later with device_start, and re-check with device_list if the call returns while still queued. These named alternatives give the agent concrete when-to-use-which guidance rather than leaving it to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources