Skip to main content
Glama

screenshot

Read-only

Capture the screen, a window, or a region as an inline image, with optional grid and window annotations to read screen coordinates for pointer clicks.

Instructions

Look at the screen, one window, or one rectangle. The image comes back in this reply -- there is nothing to Read afterwards. CROP, DO NOT SHRINK: window costs about 1300 tokens and a region strip about 160, against 1843 for the whole desktop, and all three stay legible, while scale below 1 makes small text unreadable for a saving a crop would have made anyway. Passing window AND region means a rectangle measured inside that window. annotate draws grid lines and window boxes labelled in SCREEN coordinates, so the number to pass to pointer_click can be read off the picture instead of estimated. Before reaching for this at all: ui_find and find_text answer "where is X" without an image, and every acting tool already shows you the result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
appNoAT-SPI application name for annotate.widgets, if the focused window is not the one to map.
pathNoWhere to write the PNG, e.g. /tmp/shot.png
scaleNoResize the image you are shown. Below 1 it shrinks -- measured on this 1920x1080 screen, 0.5 makes UI text hard to read and OCR fails on it entirely, so crop instead. Above 1 it enlarges, which is what a tiny crop of an icon needs.
inlineNoSet false to only write the PNG and get its path back, for a capture nobody needs to look at now.
regionNoCapture just this rectangle, in screen pixels.
windowNoCapture just this window (id, wm_class or title fragment). Captures what is ON SCREEN there, so anything in front of it is included.
annotateNotrue for grid + window boxes, or an object: {grid: true|<spacing px>, windows: bool, widgets: bool, limit: int}.
include_cursorNo
Install Server

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses important behaviors: the image is returned inline with nothing to Read afterwards, window captures reflect whatever is on screen including occluding content, annotate labels are in SCREEN coordinates, and scale below 1 harms readability. These are genuinely useful behavioral details not present in the structured fields.

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?

The description is longer than average but every sentence earns its place: primary behavior, token costs, crop advice, combination semantics, coordinate labeling, and alternatives. It is front-loaded with the core outcome before diving into tradeoffs.

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?

With no output schema, the description properly explains return behavior. It covers capture targets, inline vs file-only behavior, scaling pitfalls, occlusion semantics, coordinate conventions, and alternative tools. For an 8-parameter screenshot tool, this is sufficiently complete.

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 high (88%), so the baseline is 3, and the description adds real value beyond the schema: scale cost/readability tradeoffs, window+region composition, and annotate's coordinate purpose. However, include_cursor has no schema description and is not mentioned in the description, leaving one parameter fully undocumented.

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 opens with a specific verb and resource: 'Look at the screen, one window, or one rectangle,' and clarifies the immediate return behavior ('image comes back in this reply'). It also differentiates from siblings by naming ui_find and find_text as non-image alternatives and noting that acting tools already show results.

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?

It gives explicit when-not-to-use guidance: ui_find and find_text answer 'where is X' without an image, and every acting tool already shows the result. It also gives concrete crop-vs-shrink guidance with token cost comparisons and explains the window+region combination semantics, so an agent can choose the right capture mode.

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

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/tristanmuzzu/deskwright'

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