Skip to main content
Glama

legs_open_app

Launches an allowlisted installed application after a fresh approval, enabling agents to open approved desktop apps while respecting configured permissions.

Instructions

Launch an allowlisted installed application (e.g. 'notepad'). The allowlist lives in YOUR permissions.json (allowed_applications) — empty by default. Launching requires the app in your allowlist plus a fresh reflex_ask() approval.

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": {
      "application": "<application>"
    },
    "name": "legs_open_app"
  }
}

Input Schema

NameRequiredDescriptionDefault
applicationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

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 full behavioral burden and does meaningful work: it discloses the allowlist gate, that the list is empty by default (so most calls fail out of the box), and that a per-call approval handshake is mandatory. It does not describe what happens after a successful launch (process handle, blocking vs non-blocking) or the failure mode when the app is missing.

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 short sentences, front-loaded with the action, then the gating configuration, then the approval requirement — no filler or repetition.

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 one-parameter tool with no output schema and no annotations, the definition covers the critical unknowns: where the allowlist lives, its default state, and the approval requirement. The remaining gap is post-launch behavior and error semantics, which is minor given the tool's simplicity.

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 0% for the single 'application' parameter, so the description must compensate. It does partly, by showing the expected value form ('notepad') and making clear the string is matched against an allowlist, but it does not state whether a full path, bundle identifier, or arguments are accepted.

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 ('Launch an allowlisted installed application') and gives a concrete example ('notepad'), so the action is unambiguous. It does not contrast itself with lookalike siblings such as body_open_external or hands_open, leaving the agent to infer the boundary.

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 spells out the precondition stack clearly: the app must appear in allowed_applications in permissions.json and a fresh reflex_ask() approval is required, which effectively tells the agent which sibling to call first. It stops short of naming explicit 'do not use this when...' cases or alternatives for non-installed/non-allowlisted targets.

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