Skip to main content
Glama

capture_window

Captures a specified window or the full screen to a PNG file, enabling AI agents to inspect and automate desktop GUI applications.

Instructions

Capture a window (or the full screen if hwnd=0) to PNG.

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": {
      "out": "<out>"
    },
    "name": "capture_window"
  }
}

Input Schema

NameRequiredDescriptionDefault
outYesoutput PNG path
hwndNo
dry_runNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

C2.7/5.0
Behavior2/5

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

With no annotations, the description carries the full disclosure burden and omits the most consequential trait: dry_run defaults to true, so a naive call likely does not produce a PNG at all. It also says nothing about overwriting an existing file at `out`, permissions, or whether the target window must be unminimized.

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?

A single front-loaded sentence with no filler; the special-case note is parenthetically attached rather than buried. It is efficient, though its brevity shades into under-specification rather than pure conciseness.

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

Completeness2/5

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

For a file-producing capture tool with no annotations and no output schema, the description leaves too much unsaid: the dry_run default, output path handling, and any failure modes for invalid hwnd values. The agent cannot reliably call this correctly from the description alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, so the description must compensate and only partly does: it explains hwnd semantics (0 = full screen), which the schema leaves undocumented. The dry_run parameter — the one with a behavior-changing default — gets no explanation anywhere, leaving an agent likely to mis-invoke the tool.

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?

"Capture a window ... to PNG" states a specific verb (capture), resource (window), and output format (PNG), and clarifies the special case where hwnd=0 means full screen. It does not distinguish itself from sibling screenshot-style tools such as browser_shot or grid, so it stops short of a 5.

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

Usage Guidelines2/5

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

The only conditional given is hwnd=0 meaning full screen, which is a parameter behavior rather than usage guidance. There is no statement of when to prefer this over browser_shot, grid, or anchor_probe, and no prerequisites such as needing the window to be visible or foregrounded.

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