Skip to main content
Glama

Manage a window

window
DestructiveIdempotent

Close a selected desktop application by ID, title, or app name, read back its state, and report any save prompt without answering.

Instructions

close: close the window (one close message, read back; a "save?" prompt is reported, never answered).

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

Input Schema

NameRequiredDescriptionDefault
actionYes
windowNoWindow id from windows, or a unique part of its title or app; omitted: the window of the last look

Output Schema

NameRequiredDescriptionDefault
stateYesclosed, hidden or open
statusYesOutcome: opened, verified, unknown, prompted, unmet, sent-unconfirmed…
promptsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.7.4
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "prompts": {
      +      "items": {
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "state": {
      +      "description": "closed, hidden or open",
      +      "type": "string"
      +    },
      +    "status": {
      +      "description": "Outcome: opened, verified, unknown, prompted, unmet, sent-unconfirmed…",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "status",
      +    "state"
      +  ],
      +  "type": "object"
      +}
  2. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructive=true and readOnly=false, but the description adds genuinely useful behavioral detail beyond them: exactly one close message is sent, the result is read back, and a 'save?' prompt is reported but never answered — meaning unsaved data will be silently lost. It does not mention idempotency or the openWorld implication.

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 keyed to the action name, with the risk note packed into a parenthetical. Nothing is wasted and the most important caveat appears immediately.

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?

An output schema exists, so return values need not be described, and the key hazard (unanswered save prompt) is disclosed. Minor gaps remain: behavior when the window cannot be resolved, and whether more actions are planned given the 'Manage a window' title.

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 50%; the `window` parameter is thoroughly documented in the schema (id, unique title/app fragment, or last-look default). The description explains the `action` enum value's semantics, which the schema leaves bare, but adds no resolution or fallback detail for the `window` param.

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?

States a specific verb and resource: 'close: close the window'. The parenthetical clarifies the mechanics of the close operation. It is clearly distinct from siblings (windows/look/act/launch) by implication, though it never names an alternative or says this tool only handles closing.

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 only implied — an agent infers 'call this when you want to close a window'. There is no explicit statement about when to use it versus `windows` (to find a target) or `look` (to inspect before closing), and no prerequisites are given.

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