Skip to main content
Glama
Sign In
gwagent

gwagent

by vcnngr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

ui_global_action

Trigger Android system actions—back, home, recents, notifications, quick settings, lock screen, power dialog, or screenshot—to control device UI.

Instructions

Perform a system action like the navigation buttons or the status bar do.

lock_screen turns the screen off and locks the phone (the next UI op unlocks it); take_screenshot saves an image in the phone's gallery (prefer ui.screenshot); power_dialog needs the on-phone server.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "ui_global_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesback, home, recents, notifications, quick_settings, power_dialog, lock_screen or take_screenshot.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and delivers meaningful side-effect disclosure: lock_screen turns off and locks the phone (with the recovery path that the next UI op unlocks it), take_screenshot writes to the gallery, and power_dialog has an infrastructure prerequisite. Gaps remain for the other five actions, whose on-screen state effects are unstated.

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?

Purpose is front-loaded in a single sentence, then the caveats are grouped by action with semicolons. The line-broken formatting is slightly awkward but every sentence adds information; nothing is padding.

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 single required enum parameter with no output schema and no annotations, the description covers the surprising cases and prerequisites well. It would be fully complete with a note on what notifications/quick_settings actually do (toggle vs open panel) and whether any action alters persistent state.

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%, but the schema enum merely lists the values, so the description's per-value notes for lock_screen, take_screenshot, and power_dialog add genuine semantics the schema lacks. The remaining values (back, home, recents, notifications, quick_settings) are left to inference, which keeps it below a 5.

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?

States a concrete verb and resource: 'perform a system action like the navigation buttons or the status bar do', which frames it as global device-level actions rather than in-app gestures. The enum plus the named special cases make it distinct from ui_tap/ui_swipe, though it doesn't explicitly contrast against ui_key or device_sleep.

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

Usage Guidelines3/5

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

Usage is implied through the special-case notes: 'prefer ui.screenshot' explicitly routes the screenshot case to a sibling, and the power_dialog server requirement is stated. However, no guidance is given for when to use back/home/recents versus ui_key or when notifications/quick_settings should be triggered from this tool.

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

Deploy Server

Other Tools