Skip to main content
Glama

screenshot_background

Capture hidden, minimized, or background windows without bringing them to the foreground using the Win32 PrintWindow API. Use this tool when windows must remain hidden or cannot be made visible for capture.

Instructions

Purpose: Capture a window that is hidden, minimized, or behind other windows using Win32 PrintWindow API. Details: Uses PW_RENDERFULLCONTENT (fullContent=true, default) for GPU-rendered content in Chrome, Electron, and WinUI3 apps. Supports same detail and dotByDot modes as screenshot. Default mode scales to maxDimension=768; dotByDot=true gives 1:1 WebP with origin in response — compute screen coords: screen_x = origin_x + image_x. grayscale=true reduces size ~50%. dotByDotMaxDimension caps resolution; response includes scale (screen_x = origin_x + image_x / scale). Prefer: Prefer screenshot(windowTitle=X) for visible windows (faster, no API overhead). Use screenshot_background when the window must stay hidden or cannot be brought to foreground. Caveats: Default (scaled) mode: image pixels ≠ screen pixels — always use dotByDot=true + origin for mouse_click coords. Set fullContent=false for legacy or game windows where GPU rendering causes 1-3s delay or black capture. Some DX12 games may not capture correctly even with fullContent=true.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
windowTitleYesTitle (partial match) of the window to capture
regionNoCapture only this sub-region of the window (window-local image coordinates). Coordinates are in image pixels, not screen pixels (may differ on high-DPI). Useful to exclude browser chrome (tabs/address bar): e.g. {x:0, y:120, width:1920, height:900}.
maxDimensionNoMax width or height in pixels (default 768). Use 1280 to read small text or fine UI details.
dotByDotNo1:1 pixel mode — no scaling, WebP compression. When region is also specified, origin reflects the window + region offset for coordinate math.
dotByDotMaxDimensionNoCap the longest edge (pixels) when dotByDot=true. Response includes scale factor: screen_x = origin_x + image_x / scale.
grayscaleNoConvert to grayscale. Reduces file size ~50% for text-heavy content.
webpQualityNoWebP quality when dotByDot=true.
fullContentNoUse PW_RENDERFULLCONTENT flag (default true) to capture GPU-rendered windows (Chrome, Electron, WinUI3). Set false for legacy mode (faster, but GPU windows may appear black). If this call hangs on a game/video window, retry with fullContent=false.
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 of behavioral disclosure and excels. It details performance characteristics (e.g., 'faster, no API overhead' for screenshot, '1-3s delay or black capture' for certain modes), technical constraints (e.g., 'Some DX12 games may not capture correctly'), and practical implications (e.g., 'image pixels ≠ screen pixels' in default mode). This provides rich context beyond basic functionality.

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?

The description is well-structured with clear sections (Purpose, Details, Prefer, Caveats) and front-loaded key information. It is appropriately sized for a complex tool with many parameters and behavioral nuances, though it could be slightly more concise in the Details section without losing clarity.

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?

Given the tool's complexity (8 parameters, no annotations, no output schema), the description is highly complete. It covers purpose, usage guidelines, behavioral traits, parameter implications, and caveats. It compensates for the lack of annotations and output schema by providing detailed operational context, making it sufficient for an agent to use the tool effectively.

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?

The schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds some semantic context (e.g., explaining the implications of dotByDot mode for coordinate math and recommending fullContent=false for specific cases), but most parameter details are covered in the schema. This meets the baseline of 3 for high schema coverage.

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?

The description explicitly states the tool's purpose: 'Capture a window that is hidden, minimized, or behind other windows using Win32 PrintWindow API.' It clearly distinguishes from its sibling 'screenshot' by specifying it's for hidden/minimized/background windows versus visible windows, making the distinction explicit.

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?

The description provides explicit guidance on when to use this tool versus alternatives: 'Prefer screenshot(windowTitle=X) for visible windows (faster, no API overhead). Use screenshot_background when the window must stay hidden or cannot be brought to foreground.' It also includes caveats about specific scenarios (e.g., legacy/game windows) and parameter settings for optimal use.

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/Harusame64/desktop-touch-mcp'

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