glovebox-mcp

Overview Schema Source Related Servers Discussions Admin

window_info

Checks the active window's title and geometry and lists visible windows on an instance, providing an image-free way to confirm browser navigation or that an app opened.

Instructions

The active window's title + geometry and the list of visible windows on an instance — a cheap, image-free way to confirm navigation (browser titles follow the page) or that an app opened.

Returns {"ok", "instance", "active": {id, title, x, y, width, height, pid} | null, "windows": [{id, title}, …] (visible, capped at 50), "count"}. "active" is null when no window has focus yet (fresh instance) — that is reported, not an error. Fails (isError) if the instance is down.

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": "window_info"
  }
}

Input Schema

Name	Required	Description	Default
`instance`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.3.0Nov 6, 2026

TDQS

A3.9/5.0

Behavior4/5

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

With no annotations, the description carries the behavioral burden well: it says active can be null on a fresh instance without being an error, caps visible windows at 50, and fails if the instance is down. It does not explicitly state read-only side effects or permissions, but the 'info' framing and failure behavior give substantial context.

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?

The description is front-loaded with purpose and usage, then details return behavior and failure conditions. It is efficient, though it repeats return structure even though an output schema exists.

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 simple one-parameter tool with an output schema, the description covers purpose, usage, and key behavioral edge cases. The main gap is the undocumented 'instance' parameter, which matters when the agent needs to target a non-default instance.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description needs to compensate for the single 'instance' parameter. It implies that windows are retrieved for an instance and that a down instance causes failure, but it does not explain the parameter's meaning, default of 1, or valid instance IDs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact resource and scope: the active window's title and geometry plus visible windows on an instance. The phrase 'image-free' distinguishes it from visual siblings such as screenshot and parse_screen, so an agent can identify its role immediately.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage contexts: confirming navigation via browser titles or confirming that an app opened. The image-free framing implies that screenshot or parse_screen should be used when pixels are needed, but it does not explicitly name alternatives or exclusions.

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