Skip to main content
Glama

read_screenshot

Capture a window or full-screen screenshot for visual context, scaled to a maximum edge length. Optionally save as PNG instead of returning image tokens.

Instructions

Picture of one window (or the whole screen without window), longest side max_edge px. A window is captured in the background on Hyprland; elsewhere it comes to the front. Costs image tokens: prefer read_window. With file, saves a PNG there instead.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "read_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNoNew absolute path ending in .png
windowNoWindow id from read_windows
max_edgeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, but say nothing about side effects. The description adds real context: the window may be raised to the front on non-Hyprland systems (a visible side effect on the user's desktop) and that supplying `file` writes a PNG to disk. It does not cover failure modes for an invalid window id or what the returned image looks like, so this is solid but not complete.

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?

Three tight clauses with no filler: capture scope first, then the platform-specific side effect, then the cost/routing hint, then the file alternative. The parenthetical "(or the whole screen without window)" is slightly clipped but still parses correctly.

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?

For a 3-parameter, no-output-schema tool, the description covers what is produced, the scaling rule, the disk-write alternative, and the token cost that drives tool choice. Only error behavior for a bad window id or unwritable path is missing, which is minor.

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?

With 67% schema coverage, the description adds genuine meaning: omitting `window` means whole-screen capture, `max_edge` bounds the longest side (semantics the schema only gives as a numeric range), and `file` causes the PNG to be saved "instead" of returned. Only `window`'s source is left to the schema's "Window id from read_windows".

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?

"Picture of one window (or the whole screen without window)" states the resource and its two capture modes, plus the max_edge constraint, so an agent knows this produces an image rather than window metadata. It is distinguishable from read_window/read_windows, though the verb is nominal ("Picture of") rather than an explicit action.

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?

"Costs image tokens: prefer read_window" gives an explicit alternative and the condition (token cost) that selects it. It stops short of saying when a screenshot is unavoidable — e.g. when only visual layout matters — so there is no explicit when-not beyond the cost preference.

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