Skip to main content
Glama
Sign In
computer-use

computer-use

by Cassius-stack
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

manage_windows

Arrange multiple macOS windows with preset layouts or batch move, resize, minimize, raise, activate, and close operations to organize your workspace.

Instructions

Control and arrange multiple macOS windows in one click: apply automatic multi-window layouts (tile_left_right, tile_grid, quadrants, cascade, maximize, center, left_half, right_half, top_half, bottom_half) or batch explicit move/resize/minimize/unminimize/raise/activate/close operations.

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": "manage_windows"
  }
}

Input Schema

NameRequiredDescriptionDefault
gapNoPixel gap between tiled windows (default 8).
layoutNoOptional multi-window layout preset to apply to 'targets'.
targetsNoTarget window IDs (numbers), app names (strings), or { window_id, app, window_title } selectors for 'layout'.
activateNoRaise arranged windows after applying layout (default false).
operationsNoExplicit per-window management operations to execute in batch.
display_indexNoDisplay index for layout preset (0 = primary display).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.0.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the mutating action set (including close and quit_app) plus defaults like gap=8 and activate=false. It omits material behavior: that close/quit are irreversible, that Accessibility permissions are typically required for macOS window control, and whether the batch is atomic or partially applied on error.

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?

Front-loaded with the core purpose and packed into a single sentence with the two alternative modes laid out parenthetically. The enumerated lists of ten layouts and eleven actions are long but functional rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All six parameters are optional and there is no output schema or annotations, so the description must explain behavior on its own; it covers the two modes but not the no-argument case, error/partial-failure behavior, or permission prerequisites. Adequate for a moderately complex orchestration tool, but with clear gaps.

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 100%, so the baseline is 3, and the description adds meaning by grouping the parameters into two distinct modes (layout+targets+gap+display_index vs. operations), clarifying how the optional fields relate. The individual field semantics still live entirely in the schema.

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?

Names a specific verb (control/arrange) and a specific resource (multiple macOS windows), then enumerates the two modes of operation: layout presets and batched explicit operations. An agent can tell this is a multi-window orchestrator rather than a single-window tool like window_action, though it never names a sibling explicitly.

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?

Usage is implied by the two named modes (apply a layout preset vs. run a batch of explicit operations), and the phrase 'in one click' signals batching over repeated single calls. However, it never states when to prefer this over window_action or batch_execute, nor what happens if neither layout nor operations is supplied.

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

Deploy Server

Other Tools