Skip to main content
Glama

Take Screenshot

screenshot
Destructive

Capture a single PNG of the full screen, monitor, window, or region and return it inline and by file path for on-screen verification.

Instructions

Capture one PNG of the screen, a monitor, a window, or a region, returned inline and by path.

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": {
      "target": "<target>"
    },
    "name": "screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
outputNoOptional output .png path. Defaults to a file under SCREENCAST_HOME/screenshots.
targetYesfull | monitor:<i> (0 = primary) | window:<title> (or window:exe=<app.exe> / window:hwnd=<n>) | region:<x>,<y>,<w>,<h>. Titles match exactly, else as a substring; topmost wins.
backendNogdigrab (default, ~0.2 s): what is visible. wgc (window:, FFmpeg 8+, ~1-2 s): the window even if covered.
overwriteNoAllow replacing an existing file at the output path (default false).
exactTitleNowindow: targets match the whole title only, never a substring (default false).
returnImageNoReturn the image inline (default true; the PNG on disk stays full size).
maxImageWidthNoMax inline image width (default 1280).

Output Schema

NameRequiredDescriptionDefault
targetYes
backendYes
outputPathYes
inlineImagesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.47.0
    • changedInput schema / properties / backend / description
      Previous value: -"gdigrab (default, ~0.2 s) captures what is visible on screen. 'wgc' (window: targets only, FFmpeg 8+) captures the window's own surface through Windows Graphics Capture, even when other windows cover it; slower (~1-2 s)."New value: +"gdigrab (default, ~0.2 s): what is visible. wgc (window:, FFmpeg 8+, ~1-2 s): the window even if covered."
    • changedInput schema / properties / exactTitle / description
      Previous value: -"For window: targets, match only a window whose title equals the given title (case-insensitive); never fall back to a substring match. Default false."New value: +"window: targets match the whole title only, never a substring (default false)."
    • changedInput schema / properties / maxImageWidth / description
      Previous value: -"Downscale the inline image to at most this width (default 1280)."New value: +"Max inline image width (default 1280)."
    • changedInput schema / properties / returnImage / description
      Previous value: -"Also return the screenshot inline as an image the model can view directly (default true). The PNG on disk is always full resolution."New value: +"Return the image inline (default true; the PNG on disk stays full size)."
    • changedInput schema / properties / target / description
      Previous value: -"Capture target: 'full' | 'monitor:<index>' | 'window:<title>' (or window:exe=<app.exe> / window:hwnd=<handle>) | 'region:<x>,<y>,<w>,<h>'. window: captures the on-screen rectangle the window occupies as currently displayed - it must be visible, on top, and not minimized (case-insensitive exact title, else substring; topmost match wins)."New value: +"full | monitor:<i> (0 = primary) | window:<title> (or window:exe=<app.exe> / window:hwnd=<n>) | region:<x>,<y>,<w>,<h>. Titles match exactly, else as a substring; topmost wins."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": {},
      +  "properties": {
      +    "backend": {
      +      "type": "string"
      +    },
      +    "inlineImages": {
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "outputPath": {
      +      "type": "string"
      +    },
      +    "target": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "outputPath",
      +    "target",
      +    "backend",
      +    "inlineImages"
      +  ],
      +  "type": "object"
      +}
  2. First observedv0.32.0

TDQS

B3.4/5.0
Behavior3/5

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

The description discloses the key side effect channel — the capture is written to a path as well as returned inline — which aligns with destructiveHint=true and readOnlyHint=false rather than contradicting them. However, it never mentions that writing fails if the path exists unless overwrite is set, nor the default location, so the destructive/write profile is only partially explained beyond the annotations.

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?

A single front-loaded sentence with zero filler; the verb, artifact, target scopes, and return modes all land immediately.

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?

With a full output schema and complete parameter documentation, the description only needs to orient the agent, which it does. The remaining gap is that the write-to-disk side effect and its overwrite gating are implied rather than stated, which matters given destructiveHint=true.

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 description coverage is 100%, so all seven parameters are already documented in detail (including backend tradeoffs and default values), which establishes the baseline of 3. The description only adds the framing that output is dual-channel (inline plus file), which lightly motivates returnImage and output but adds no new semantics.

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 specific verb (Capture), an explicit format (one PNG), and enumerates the four target scopes (screen, monitor, window, region), plus the two return channels. An agent knows exactly what it gets. It stops short of naming which sibling handles adjacent jobs (sample_frames, contact_sheet, list_targets), so it is clear but not differentiated.

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?

There is no statement of when to reach for this versus siblings like sample_frames, contact_sheet, or list_targets, and no exclusions or prerequisites. Usage is only inferable from the tool name and the enumerated targets.

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