Skip to main content
Glama

screenshot

Capture the game and return it as an image.

Instructions

Capture the game and return it as an image.

By default grabs the Deadlock window itself via X11 (works even when other windows cover it, no focus change). If the window can't be captured (minimised, not found) this is an error, not a picture of the desktop. full_screen=True captures the whole screen instead, other windows included. crop: 'WxH+X+Y' in captured-image pixels (the game window's, e.g. '800x800+0+1100' for the bottom-left HUD), applied before resizing — use it to inspect small HUD details. A crop that fails is an error, not an uncropped image.

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": "screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
cropNo
max_widthNo
full_screenNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full load and does well: it discloses the X11 window-targeting behavior, that capture works despite occlusion and without focus changes, and that failures surface as errors rather than silent fallbacks (desktop picture, uncropped image). It does not mention image encoding/format or any cost or permission considerations, which is a minor omission for a read-only capture tool.

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?

Front-loads the core action, then layers default behavior, failure semantics, and per-parameter detail in a tight, scannable sequence. The paired 'this is an error, not X' clauses for both capture and crop prevent a common misfire and each earns its place.

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?

No output schema or annotations exist, so the description is the only source, and it covers capture scope, fallback/error behavior, crop geometry, and resize ordering. The remaining gap is max_width — its meaning, units, and upscaling-vs-downscaling behavior are not explained, and the return image format is unstated.

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 description coverage is 0%, so the description must compensate, and it largely does: crop gets an exact 'WxH+X+Y' format, a coordinate reference frame (captured-image pixels, game window's), a worked example, and ordering relative to resizing. full_screen is explained in behavioral terms. Only max_width is left merely implicit ('applied before resizing'), with its default and units not discussed.

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?

States a specific verb and resource ('Capture the game and return it as an image') and immediately scopes it to grabbing the Deadlock window via X11 rather than the desktop. An agent can tell exactly what it gets back and how it differs from any other utility in the sibling list.

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?

Gives concrete when-to-use guidance: crop is for inspecting small HUD details, full_screen=True for the whole desktop. It also names the failure conditions (minimised, not found) that select the error path. No explicit exclusions exist, but no competing capture tool is present either, so the routing guidance is adequate.

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