Skip to main content
Glama

Take and boot the emulator

emu_start
Idempotent

Lease and boot a shared Android emulator, or reuse a running one, then prepare it for automation: animations off, screen on, keyguard dismissed, clock reset. Use before device-changing tools.

Instructions

Lease the AVD to this session and boot it (or reuse it when it already runs), then make it predictable for automation (animations off, screen stays on, keyguard dismissed, clock reset). Call this before any other device-changing tool. On BUSY another session holds the emulator: do not retry in a loop and never release its lease; wait, or ask the person. Runs as a job: if the result is a job_id, call emu_job with it. Calling it again under your own lease only renews the lease. Always call emu_release when done.

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": "emu_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
avdNoAVD name (default "unity-test", or the EMU_AVD environment variable of the server).
hoursNoLease length in hours from now (default 4).
headlessNoStart the emulator without a window (default false).
wait_secNoHow long this call waits for the job (default 50, max 600). If the job is still running, the call returns a job_id for emu_job.
cold_bootNoIgnore the quick-boot snapshot (slower, a clean boot; default false).
boot_timeout_secNoTime for the emulator to appear and finish booting (default 300).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world, and the description confirms the idempotency claim concretely ('reuse it when it already runs', 'Calling it again under your own lease only renews the lease'). It adds lease ownership semantics, the BUSY failure mode, the job-handoff mode, and the device mutations performed (animations off, keyguard dismissed, clock reset) — all beyond what the annotations convey.

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?

Front-loads the primary action and its result, then layers ordering, failure handling, job routing, and cleanup in short clauses. Nearly every clause carries an actionable instruction, with no filler or repetition.

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?

For a mutating, 6-parameter, job-capable tool with no output schema and only coarse annotations, the description covers the gaps that matter: lease contention, retry policy, job polling, and required release. Nothing an agent needs in order to invoke or recover from this call is missing.

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 100% and every parameter (avd, hours, headless, wait_sec, cold_boot, boot_timeout_sec) already carries its own default and bounds, so the description is not obligated to restate them. Its only added meaning is the workflow link between wait_sec and a returned job_id, which is useful but not a parameter-level explanation. Baseline 3 is appropriate.

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 concrete verb+resource pair ('Lease the AVD ... and boot it'), adds the reuse case, and enumerates the post-boot normalization steps so the agent knows exactly what state it gets. It also distinguishes itself from emu_job, emu_release, and implicitly emu_renew by explaining the re-call renewal behavior.

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?

Gives explicit ordering ('Call this before any other device-changing tool'), an explicit when-not path with anti-patterns on BUSY ('do not retry in a loop and never release its lease'), a follow-up route when a job_id is returned, and a closing cleanup requirement ('Always call emu_release when done').

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