Skip to main content
Glama
Sign In
NexusWindows for Claude

NexusWindows for Claude

by pironjulien
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

windows

Read-onlyIdempotent

Lists open apps and dialogs front-to-back with handle, title, process, UI framework, and size; filter by title or process to target taskbar, desktop, or hidden app views.

Instructions

List application windows (front to back): hwnd, title, process, UI framework (Win32, WPF, Chromium…), size; [dialog of N "title"] = dialog or other window owned by window N (file picker, "Open", "Save as"); [hidden] = Store app Windows never shows (launched in the background), readable and drivable all the same. Then Windows itself: window="taskbar" and window="desktop" (icons). filter: part of a title or process name.

Input Schema

NameRequiredDescriptionDefault
filterNo

Output Schema

NameRequiredDescriptionDefault
windowsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.7.4
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$defs": {
+    "WindowRow": {
+      "properties": {
+        "foreground": {
+          "title": "Foreground",
+          "type": "boolean"
+        },
+        "framework": {
+          "title": "Framework",
+          "type": "string"
+        },
+        "height": {
+          "title": "Height",
+          "type": "integer"
+        },
+        "hidden": {
+          "description": "Store app never shown by Windows, drivable all the same",
+          "title": "Hidden",
+          "type": "boolean"
+        },
+        "hwnd": {
+          "title": "Hwnd",
+          "type": "integer"
+        },
+        "maximized": {
+          "title": "Maximized",
+          "type": "boolean"
+        },
+        "minimized": {
+          "title": "Minimized",
+          "type": "boolean"
+        },
+        "owner": {
+          "description": "hwnd of the owner window for a dialog, 0 otherwise",
+          "title": "Owner",
+          "type": "integer"
+        },
+        "process": {
+          "title": "Process",
+          "type": "string"
+        },
+        "surface": {
+          "description": "Windows surface (\"taskbar\", \"desktop\"...), empty for an application window",
+          "title": "Surface",
+          "type": "string"
+        },
+        "title": {
+          "title": "Title",
+          "type": "string"
+        },
+        "width": {
+          "title": "Width",
+          "type": "integer"
+        }
+      },
+      "required": [
+        "hwnd",
+        "title",
+        "process",
+        "framework",
+        "width",
+        "height",
+        "minimized",
+        "maximized",
+        "foreground",
+        "hidden",
+        "owner",
+        "surface"
+      ],
+      "title": "WindowRow",
+      "type": "object"
+    }
+  },
+  "properties": {
+    "windows": {
+      "items": {
+        "$ref": "#/$defs/WindowRow"
+      },
+      "title": "Windows",
+      "type": "array"
+    }
+  },
+  "required": [
+    "windows"
+  ],
+  "title": "WindowsOutput",
+  "type": "object"
+}
  2. First observedv3.3.1

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower; the description still adds substantial behavioral context: the front-to-back ordering, the '[dialog of N]' ownership notation for file pickers, and the '[hidden]' semantic that Store apps launched in the background are still readable and drivable. It stops short of describing pagination or volume limits, but the added semantics are meaningful.

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?

A single tightly packed passage that is front-loaded with the core purpose before examples. Density is high and the 'Then Windows itself' transition is slightly cryptic, but no clause is filler — each defines an output field, a notation, or a special-case window.

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?

Given one optional parameter, an output schema, and full annotation coverage, the description supplies what structured data doesn't: what the list represents, how owned dialogs and hidden windows appear, and what the filter matches. An agent can call this correctly without further information.

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 0% and the schema only names 'filter' with a null default, so the description carries the burden and does so: 'filter: part of a title or process name' tells the agent it is a substring match over two distinct fields, which the schema does not convey. It doesn't say whether matching is case-insensitive, which is a minor gap.

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?

Opens with a specific verb+resource ('List application windows') and immediately defines the scope and ordering ('front to back') plus the fields returned, so the agent knows exactly what this produces. It doesn't explicitly contrast itself with the sibling 'window' tool (likely for acting on a single window), so it falls short of full sibling differentiation.

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?

Gives real usage context: how to reach the taskbar and desktop via window="taskbar"/"desktop", and how the filter argument matches. However, there is no explicit statement of when to prefer this over the sibling 'window' tool or how it relates to 'act'/'look' in a typical workflow.

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