Skip to main content
Glama

browser_open_tab

Open one or multiple controllable browser tabs in the background and return their indexed DOM/AX trees for automation or inspection.

Instructions

Open one or multiple controllable browser tabs in the background (uses live Antigravity Extension Chrome Tab Group when connected, or auto-connects to CDP / auto-launches Chromium, or opens Safari tabs when browser_id='safari') and return their indexed DOM/AX trees.

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": "browser_open_tab"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoURL to open in a new tab.
urlsNoMultiple URLs to open concurrently in separate tabs in one call.
activeNoWhen opening in an extension browser, bring the new tab to the foreground (default false so the user's active tab is undisturbed).
ungroupNoIf true, do not place the newly created extension tab into a Tab Group.
visibleNoIf false on 'default'/'iab', runs in headless background browser; if true, opens in a visible browser window.
window_idNoOptional Chrome windowId to open the tab inside.
browser_idNoTarget browser ('default' prefers live Antigravity Extension browser, then CDP, then managed Chromium; 'brave'/'chrome'/'edge'/'arc' targets that browser; 'iab' forces background managed browser; 'safari' opens in Safari).
session_idNoLogical session ID for grouping agent-created tabs (default 'default').
group_colorNoTab Group color for newly created extension tabs (default 'cyan').
group_titleNoTab Group title for newly created extension tabs (default 'Antigravity').
return_stateNoReturn initial indexed AX state for each opened tab (default true).
include_cursorNoComposite in-tab virtual cursor overlay in screenshot (default false).
include_screenshotNoInclude initial live CDP JPEG screenshot(s) (default false).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.0.0

TDQS

A3.6/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full load, and it does substantial work: it discloses the backend resolution order (live extension tab group → CDP → auto-launched Chromium → Safari via browser_id), that tabs open in the background by default, and that indexed DOM/AX trees are returned. It stops short of stating permission requirements or what happens with zero URL parameters.

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?

Purpose is front-loaded in the first clause, followed by the backend detail, so an agent gets the gist immediately. It is a single heavily nested sentence with stacked parentheticals, which is dense but not padded.

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 13-parameter tool with no annotations and no output schema, the description covers return content and backend behavior reasonably well. It is silent on the zero-required-parameter case (what a call with no url/urls does) and on interactions between window_id, visible, and browser_id, which are real gaps for a tool this configurable.

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%, so the schema already documents all 13 parameters, including the browser_id fallback chain and default values. The description reinforces only the browser_id='safari' case and the background default, adding little meaning beyond the structured field text.

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 ('Open') and resource ('controllable browser tabs'), plus scope ('one or multiple') and a return payload ('indexed DOM/AX trees'). It does not name a sibling such as browser_tab_action or browser_manage to sharpen the boundary, so it lands at strong-but-not-fully-differentiated.

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: the phrase 'controllable browser tabs' and the returned DOM/AX trees suggest it is the setup step before interacting with a page. There is no explicit when-to-use vs. when-to-use-an-alternative guidance, no note on url vs. urls selection, and no prerequisites stated.

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