Skip to main content
Glama

window

Destructive

Move, resize, minimize, restore, or close a desktop app by title or handle without activating it.

Instructions

Move ('x,y'), resize ('w,h'), minimize, restore (back behind the user's windows) or close a window without activating it.

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": {
      "title": "<title>",
      "action": "<action>"
    },
    "name": "window"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYespart of the window title (case-insensitive; an exact title wins) or a handle from list_windows (0x...)
valueNox,y or w,h
actionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety bar is partly covered. The description adds genuinely non-obvious behavior beyond that: all operations run without activating the window, and restore places it 'back behind the user's windows'. It stops short of saying that close is irreversible or what happens when minimize/close receive no value.

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?

A single front-loaded sentence enumerating actions with their argument shapes inline. No filler, and the scope qualifier ('without activating it') is placed at the end where it reads as a constraint on the whole list.

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?

With three parameters, no output schema, and annotations carrying the destructive read profile, the description covers the action set and the key behavioral constraint. Gaps remain around failure modes, multi-match handling, and required arguments per action, but the schema's title description partially compensates.

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 67% and the description meaningfully binds the loose 'value' parameter to actions — 'x,y' for move, 'w,h' for resize — which the schema only states generically. It does not clarify units, absolute vs. relative, or that value is irrelevant for minimize/restore/close, so it stops short of full coverage.

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 names five concrete actions (move, resize, minimize, restore, close) against a single resource (a window), so the agent knows exactly what domain this tool covers. The phrase 'without activating it' adds a distinguishing behavioral trait, but no sibling tool is named, so differentiation from ui_act or launch is left implicit.

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 rather than stated: 'without activating it' suggests this is the choice when the user's foreground window should not be disturbed. There is no explicit when-to-use or when-not-to-use rule, and no pointer to alternatives such as ui_act for window interaction that does require activation.

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