Skip to main content
Glama

Open a file, link or app

open

Opens files, folders, URLs, or apps on macOS using the system open command. Use it to launch documents, websites, or applications directly from the terminal.

Instructions

Open a file or folder, an http(s) URL, or an app (macOS open). It runs outside the sandbox: a file can be a script and a link can carry data out, so open only what the user asked for.

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": "open"
  }
}

Input Schema

NameRequiredDescriptionDefault
appNoan app name such as Safari: opens target with it, or just the app when there is no target
targetNoa file or folder path, or an http(s) URL

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.7.3
    • addedInput schema / properties / app / description
      Added value: +"an app name such as Safari: opens target with it, or just the app when there is no target"
    • addedInput schema / properties / target / description
      Added value: +"a file or folder path, or an http(s) URL"
  2. First observedv0.7.1

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only mark openWorldHint=true and destructiveHint=false; the description goes further by disclosing that execution happens outside the sandbox and that opening a script or a link with embedded data can have real side effects. That is meaningful behavioral context beyond the annotations, though it does not say what happens when called with no arguments at all.

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?

Two sentences: the capability statement first, the risk caveat second. Nothing is redundant and the important constraint is not buried.

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 two-optional-parameter tool with full schema coverage and no output schema, the description covers what can be opened and the security posture. The one gap is the zero-argument case — with no required parameters, an agent gets no guidance on what a bare call does.

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 description coverage is 100%, with both `app` and `target` documented including the app-only case. The description restates the same resource categories without adding format, path, or precedence detail, so it is a baseline-3 case where the schema does the work.

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?

The description gives a specific verb plus an enumerated resource set: 'a file or folder, an http(s) URL, or an app', and names the underlying macOS `open` primitive. It is clearly distinct from write_file or run, but it never explicitly contrasts with read_file, which an agent might otherwise confuse for viewing file contents.

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 resource list (files, URLs, apps) and there is a safety directive — 'open only what the user asked for' — but no explicit when-to-use-vs-alternative routing, e.g. no pointer to read_file for reading contents or run for execution. An agent can infer the scope but is not guided to a sibling.

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