Skip to main content
Glama

app_ensure

Ensure a desktop app is running and usable: check its state, restore a hidden window without stealing focus, or launch it by executable or Store AUMID, then wait until usability is confirmed.

Instructions

Ensure an app is alive and usable, then prove it. Reports whether the app is running, window-gone or not running; restores a hidden window without stealing focus, or launches it (exe / Store AUMID) and waits until it is actually usable. ok is true only when usability was observed, not merely when a launch was issued.

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": "app_ensure"
  }
}

Input Schema

NameRequiredDescriptionDefault
exeNoexecutable to start when the app is gone
aumidNoStore app id, e.g. Family!App
dry_runNo
timeoutNo
class_nameNo
process_nameNoprocess name, with or without .exe
title_containsNosubstring of the window title

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the burden well: it discloses that a hidden window is restored without stealing focus, that launching supports exe and Store AUMID, and that it waits for observed usability rather than returning on launch issuance. The notable omission is that it never mentions the schema's dry_run default of true, so an agent reading only the prose could assume a real launch/restore occurs when the default is a dry run.

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?

Three tight sentences, front-loaded with the outcome guarantee and the ok semantics placed last as the payoff. Every clause carries distinct information about states, focus behavior, or launch inputs.

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?

For a seven-parameter tool with no annotations and no output schema, the description does the essential work by explaining the returned state vocabulary and the meaning of ok. It falls short only on how the identification parameters (class_name, process_name, title_contains) combine to target an app and on the dry_run default.

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 57%, and the description only explains two of seven parameters, exe and aumid, giving them useful framing ('launches it'). It adds nothing about process_name, title_contains, class_name, timeout, or the critical dry_run flag, leaving half the parameters to the schema alone.

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 states a specific verb and resource ('Ensure an app is alive and usable, then prove it') and enumerates the three observed states (running, window-gone, not running). It also names the two launch mechanisms (exe / Store AUMID), which is enough to distinguish it from a plain browser_launch or launch-only sibling.

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 by the state branching: restore if the window is hidden, launch if the app is gone. However, there is no explicit guidance on when an agent should prefer this tool over launch/probe siblings such as browser_launch or anchor_probe, and no stated preconditions.

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