Skip to main content
Glama

wintool

Automate Windows GUI applications by finding, inspecting, and controlling windows. Perform operations like clicking, typing, capturing screenshots, reading clipboard images, and sending window messages for automation tasks.

Instructions

Windows GUI automation tool for finding, inspecting, and controlling windows. Find windows by title/class/PID, enumerate child controls, capture screenshots (base64 PNG), read clipboard images, read/set text, click, type, send raw messages, show/hide/minimize/maximize, move/resize, close, focus. Windows only. macOS and Linux are not supported. Operations: list, tree, find, inspect, screenshot, clipboard, gettext, settext, click, type, send, show, move, close, focus. clipboard: reads image from system clipboard and saves as PNG temp file. Use after Win+Shift+S or Copy. type: sends keyboard input. Auto-detects console windows (ConsoleWindowClass) and uses WriteConsoleInput. Tip: type + send(msg=WM_KEYDOWN, wparam=VK_RETURN) can inject commands into other terminal/IDE sessions. Works with Electron (VSCode) too.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationYesOperation: list, tree, find, inspect, screenshot, gettext, settext, click, type, send, show, move, close, focus,required
hwndNoWindow handle in hex (e.g. '0x1A2B3C'). Required for most operations except list/find
titleNoWindow title substring to search for (case-insensitive)
classNoWindow class name to search for
pidNoFilter by process ID
xNoX coordinate (client-relative) for click
yNoY coordinate (client-relative) for click
buttonNoMouse button: left (default), right, middle. For click
textNoText for type/settext operations
msgNoWindow message ID (e.g. 16 for WM_CLOSE, 274 for WM_SYSCOMMAND). For send
wparamNoWPARAM value for send operation
lparamNoLPARAM value for send operation
postNoUse PostMessage instead of SendMessage (async). Default: false
show_cmdNoShow command: show, hide, minimize, maximize, restore. For show
move_xNoNew X position for move
move_yNoNew Y position for move
widthNoNew width for move (0 = keep current)
heightNoNew height for move (0 = keep current)
max_resultsNoMaximum number of results. Default: 100, Max: 1000
save_pathNoSave image to this path instead of returning base64. For screenshot/clipboard
Behavior4/5

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

No annotations provided, so description carries full burden. Discloses specific implementation details: clipboard saves as 'PNG temp file', type operation 'auto-detects console windows (ConsoleWindowClass) and uses WriteConsoleInput', and Electron compatibility. Could improve by mentioning permission requirements or error behaviors.

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?

Well-structured with purpose front-loaded. Minor redundancy between capability list ('Find windows...close, focus') and explicit operations enumeration. Every sentence conveys distinct information (platform constraints, specific behaviors, advanced tips). Appropriate length for 20-parameter multi-operation tool.

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?

Comprehensive coverage of 14 distinct operations for a complex GUI automation tool. Addresses critical platform limitation. Missing return value documentation (no output schema present) and error handling specifics, but operational coverage is thorough.

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 has 100% description coverage, establishing baseline 3. Description adds operational context (e.g., clipboard temp file behavior, console detection) but does not significantly enhance individual parameter semantics beyond the comprehensive schema definitions.

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 explicitly states 'Windows GUI automation tool for finding, inspecting, and controlling windows' with specific verbs and resource types. It clearly distinguishes from all siblings (bash, procexec, file tools, etc.) by specifying GUI-focused capabilities unique to this server.

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 explicit platform constraint ('Windows only. macOS and Linux are not supported') and advanced usage guidance ('Use after Win+Shift+S', injection tip for VSCode/Electron). Lacks explicit alternative recommendations for non-GUI scenarios, but the platform boundary is clearly defined.

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/knewstimek/agent-tool'

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