Skip to main content
Glama

browser_manage

Manage browser sessions, Chrome Tab Groups, tab ownership, history, and bookmarks; claim tabs without moving them and finalize sessions by closing scratch tabs and detaching debuggers.

Instructions

Manage browser sessions, Chrome Tab Groups, tab ownership/lifecycle, history, and bookmarks via the Antigravity Browser Extension bridge: status, list_tab_groups, create_tab_group, group_tabs, update_tab_group, name_session, ungroup_tabs, claim_tab (in-place without moving user's tab), mark_tab ('deliverable' | 'handoff' | 'scratch'), finalize_session (closes scratch tabs + detaches debuggers so Chrome/Brave banner vanishes), search_history, list_bookmarks, create_bookmark.

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_manage"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoBookmark URL for create_bookmark.
nameNoSession / Tab Group name for name_session or group_tabs.
colorNoTab Group color.
countNoMax recent bookmarks for list_bookmarks when query is omitted (default 25).
queryNoSearch query for search_history or list_bookmarks.
titleNoTitle for Tab Group or bookmark.
actionNoBrowser management operation (default 'status').
statusNoTab lifecycle status for action='mark_tab'.
tab_idNoSingle tab ID (e.g. 'tab-1' or numeric Chrome tabId) for claim_tab / mark_tab / group_tabs.
tab_idsNoTab IDs (e.g. ['tab-1', 'tab-2'] or Chrome tabIds) for create_tab_group / group_tabs / ungroup_tabs.
activateNoFor mark_tab status='handoff': focus the tab for the user (default true on handoff).
group_idNoExisting Chrome Tab Group ID for group_tabs or update_tab_group.
collapsedNoCollapse or expand the Tab Group.
parent_idNoOptional parent bookmark folder ID for create_bookmark.
window_idNoOptional Chrome windowId filter/target.
browser_idNoOptional target extension browser ID or brand (e.g. 'brave', 'chrome', 'ext-brave').
detach_allNoFor finalize_session: detach chrome.debugger from all attached tabs across sessions.
session_idNoAgent session ID (default 'default').
max_resultsNoMax results for search_history (default 25).
close_scratch_tabsNoFor finalize_session: close unmarked agent-created scratch tabs (default true).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.0.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose a few genuinely useful behaviors: claim_tab works in-place without moving the user's tab, mark_tab assigns deliverable/handoff/scratch, and finalize_session closes scratch tabs and detaches debuggers so the Chrome/Brave banner disappears. However, the other ten actions get only a name, leaving side effects (does group_tabs move user tabs?), permission needs, and reversibility undisclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single compact sentence with no filler, so nothing is wasted. But it is a comma-delimited wall of thirteen action names with no grouping, prioritization, or front-loading of the most common path, making it hard to scan.

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?

Given 20 parameters at 100% schema coverage and no output schema, the schema does much of the work of mapping parameters to actions. What the description lacks is workflow framing and per-action side-effect disclosure for a thirteen-action mega-tool, but the essentials for invocation are largely present.

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% and each parameter already names the action it serves, so the baseline of 3 applies. The description adds little beyond the enum itself, aside from clarifying the semantics of claim_tab, mark_tab, and finalize_session, which is marginal value over structured data.

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?

Names a specific verb ('Manage') and enumerates the resource domains it covers: browser sessions, Chrome Tab Groups, tab ownership/lifecycle, history, and bookmarks, tied to the Antigravity Browser Extension bridge. The action list makes it distinguishable from siblings like browser_open_tab or browser_tab_state, though the breadth of the scope means no single purpose dominates.

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

Usage Guidelines2/5

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

The description lists what actions exist but never says when to choose browser_manage over siblings such as browser_tab_action, browser_list, or manage_windows. There are no exclusions, no prerequisites, and no ordering guidance (e.g. status → claim_tab → mark_tab → finalize_session) despite the tool clearly implying a workflow.

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