Skip to main content
Glama

desktop_open_system_surface

Open a shell surface (start menu, taskbar, dock, menu-bar extras) and return any window it presents, enabling UI automation of system surfaces.

Instructions

agent-desktop open-system-surface: Open a shell surface (start-menu, taskbar, dock, menu-bar-extras ...) and return the window it presents, if any

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": {
      "surface": "<surface>"
    },
    "name": "desktop_open_system_surface"
  }
}

Input Schema

NameRequiredDescriptionDefault
surfaceYesShell surface to open: start-menu, taskbar, system-tray, system-tray-overflow, action-center, dock, menu-bar-extras

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.4/5.0
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 one key behavior: it may return a window, or nothing ('if any'). It omits other important traits for a UI-mutating tool, such as whether the surface stays open, whether it steals focus or triggers OS overlays, and whether any permission or platform gating applies.

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?

One compact, front-loaded sentence with the resource and examples placed early. The leading 'agent-desktop open-system-surface:' prefix merely restates the tool name and earns no place, but the body is efficient.

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?

For a one-parameter tool with no output schema, the description covers what it does and that a window may or may not come back. It is incomplete about platform-dependent availability of surfaces and about side effects of opening OS shell UI, which are the main things an agent could get wrong here.

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 100% and the single parameter is a fully enumerated string, so the schema already documents valid values. The description only re-lists a subset of those enum values (start-menu, taskbar, dock, menu-bar-extras) and adds no meaning about platform applicability or how 'window'/'focused'/'menu' differ from shell surfaces. Baseline 3 applies.

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 (Open) and resource (shell surface) with concrete examples (start-menu, taskbar, dock, menu-bar-extras) and adds the outcome 'return the window it presents, if any'. It does not explicitly name the sibling it contrasts with (e.g., desktop_list_surfaces or desktop_focus_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?

Usage is only implied by the examples: an agent can infer this is the tool for popping open OS chrome rather than listing or focusing windows. There is no explicit when/when-not guidance, no note that desktop_list_surfaces should be consulted first, and no mention that a surface may not exist on the current platform.

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