Skip to main content
Glama

capture

Read-only

Takes screenshots of the full screen, a monitor, a selected region, the active app, or a specific window and returns the image; covered windows can be included.

Instructions

Screenshot: full, monitor, region, active or window (PrintWindow, works while covered). Returns the image. Capturing a minimized window restores it, so it needs bring_to_front after the user agreed.

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": {
      "mode": "<mode>"
    },
    "name": "capture"
  }
}

Input Schema

NameRequiredDescriptionDefault
hNoregion height
wNoregion width
xNoregion left
yNoregion top
modeYes
titleNopart of the window title (case-insensitive; an exact title wins) or a handle from list_windows (0x...)
monitorNomonitor index for mode=monitor
bring_to_frontNorestore and activate the window first (takes the user's focus)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With readOnlyHint=true already supplied, the description adds real behavioral context the annotations cannot: the return value ('Returns the image'), the PrintWindow rendering behavior that works even when the window is covered, and the state-changing side effect of restoring a minimized window / stealing focus via bring_to_front. It does not cover failure modes (window not found, invalid region), which keeps it at 4.

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?

Three tight clauses, front-loaded with the verb and mode list before the caveats. Dense and nearly waste-free, though the final sentence's phrasing ('it needs bring_to_front after the user agreed') is compressed to the point of slight ambiguity.

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 an 8-parameter tool with no output schema, the description covers the return value, the window-specific pitfalls, and the focus consequence of bring_to_front. Gaps remain on error behavior and on how region coordinates are interpreted, but the essentials for a correct call are present.

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 coverage is 88%, so the schema already documents x/y/w/h, title, monitor and bring_to_front. The description adds only the operational consequence of bring_to_front (focus theft, needs user consent) and does not clarify region coordinates or monitor indexing, so this is the baseline 3.

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?

The description opens with a specific verb+resource ('Screenshot') and enumerates the five capture modes matching the mode enum, plus a technical note on the window path (PrintWindow, works while covered). It does not name sibling alternatives (crop, mask, window) to route the agent away, 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 Guidelines3/5

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

Useful conditional guidance is present for one path: capturing a minimized window forces bring_to_front and requires prior user agreement. But there is no directive on when to prefer this over sibling tools such as crop or mask, and no explicit prerequisite for obtaining a handle beyond a parenthetical mention of list_windows.

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