Skip to main content
Glama

open

Boot a selected device and open an app, deep link, or URL as the automation target. Record Metro/debug hints so a later reload reuses the same session binding.

Instructions

Boot the selected device when needed, then open an app, deep link, or URL in a session. Use the app or URL inputs to choose what becomes the foreground automation target. Metro and debug runtime hints given here are recorded as the session's dev-server binding, so a later reload reuses them; a fresh open without them clears any binding left by a previous same-name session.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
appNoApp name, bundle id, package, or URL.
cwdNoWorking directory for command execution.
urlNoOptional URL passed with an app shell.
udidNoiOS device UDID selector.
debugNoEnable debug diagnostics.
forceNoOverwrite an existing --save-script target instead of refusing (alias: --overwrite).
runIdNoLease run identifier.
deviceNoDevice name selector.
serialNoAndroid device or Vega VVD serial selector.
targetNoAlias for deviceTarget on commands without a UI target field. Interaction commands reserve target for the UI element.
tenantNoRemote tenant identifier.
leaseIdNoExisting lease identifier.
sessionNoAgent-device session name.
surfaceNomacOS presentation surface to open: the app itself, the frontmost app, the desktop, or the menu bar.
testImeNoActivate the headless Android test IME for deterministic Unicode text entry (default on for emulators; opt-in on real devices).
activityNoAndroid activity name.
noRecordNoDo not record this action.
platformNoPlatform selector used to resolve a device.
relaunchNoForce relaunch.
stateDirNoAgent-device state directory.
bundleUrlNoSession-scoped bundle URL hint applied to the opened app.
deviceHubNoUse Xcode Device Hub when surfacing Apple simulators.
launchUrlNoSession-scoped launch URL hint applied to the opened app.
metroHostNoSession-scoped Metro/debug host hint applied to the opened app.
metroPortNoSession-scoped Metro/debug port hint applied to the opened app. On an emulator/simulator the host defaults to the loopback alias (Android 10.0.2.2, iOS 127.0.0.1) when --metro-host is omitted; physical devices still require an explicit --metro-host.
foregroundNo[RFC prototype] On a fresh session with no app argument, resolve the target from the sole booted iOS simulator's sole running app and include an initial interactive snapshot in the response. Fails with AMBIGUOUS_MATCH when the environment is not unambiguous (0 or 2+ booted simulators, or no confidently-detectable running app) — never guesses.
launchArgsNoLaunch arguments forwarded verbatim to the platform launch command.
saveScriptNo
includeCostNoInclude per-command agent-cost (cost.wallClockMs, …) in structuredContent. Defaults to off; the default response shape is unchanged.
deviceTargetNoDevice target form. Maps to the CLI --target flag.
daemonBaseUrlNoRemote daemon base URL.
launchConsoleNoLaunch console mode.
responseLevelNoResponse verbosity: token-cheap digest / default (today) / full. Defaults to default; the default response shape is unchanged.
daemonAuthTokenNoRemote daemon auth token.
iosXctestEnvDirNoWritable directory for iOS XCTest runner env overlays.
mcpOutputFormatNoMCP text content format. Defaults to optimized agent-friendly text; use json for JSON text. Structured content is always returned separately.
iosXctestrunFileNoExternally built iOS XCTest runner .xctestrun artifact path.
iosSimulatorDeviceSetNoiOS simulator device-set path used for device resolution.
androidDeviceAllowlistNoAndroid serial allowlist used for device resolution.
iosXctestDerivedDataPathNoDerived data path for external iOS XCTest runner execution.
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses boot-on-demand behavior, the foreground-target effect, and the stateful dev-server binding lifecycle (reuse, clearing). It does not cover all side effects, permissions, or failure modes, but provides substantive behavioral insight beyond the schema.

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?

Three sentences, no filler, and front-loaded with the core purpose. The complex dev-server binding behavior is packed into a compact, readable final sentence without unnecessary elaboration.

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

Completeness4/5

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

For a 40-parameter tool with a rich schema, the description supplies the missing integration narrative: the boot-then-open flow and session-scoped dev-server binding. It does not fully define 'session' or address no-argument invocation, but the schema covers parameter details, making the description sufficiently complete.

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 98%, so baseline is 3. The description adds meaning by tying app/url inputs to the foreground automation target, and by explaining Metro/debug hints as session dev-server bindings. This exceeds the schema's isolated parameter descriptions.

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?

Description uses specific verbs: 'Boot the selected device when needed, then open an app, deep link, or URL in a session.' It clearly distinguishes from siblings like boot (booting only) and metro (dev-server only) by focusing on opening a foreground automation target. The purpose is concrete and actionable.

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

Usage Guidelines4/5

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

Provides clear context: use app or URL inputs to choose the foreground target, and explains how Metro/debug hints become session dev-server bindings. It implies when to use the tool, but does not explicitly state exclusions or alternatives (e.g., 'for booting only, use boot').

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/callstack/agent-device'

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