Skip to main content
Glama

open_instance

Starts a new Chrome or Firefox browser instance with its own profile and assigns the label as the instance_id used by other browser-control tools.

Instructions

Starts a new browser instance, Chrome or Firefox, with its own profile; its 'label' becomes the instance_id other tools take. Fails in --user-profile mode.

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_instance"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelNoBecomes the instance_id. Default: generated.
proxyNoProxy URL; credentials go to enable_proxy_auth.
browserNo'chrome' (CDP) or 'firefox' (BiDi and RDP). Default: the server's --browser. Prefer Chrome unless the user asks for Firefox.
featuresNoPresets: WEBGL_SOFTWARE (software WebGL, for GPU-less hosts). Default: none.
headlessNoDefault: the server's --headless.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0-rc.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare destructiveHint=false, so the description carries most of the burden and does add real context: a new isolated profile is created, the label propagates as instance_id to other tools, and there is a known failure mode. It doesn't say whether the browser window is visible or what happens if an instance with the same label already exists.

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, front-loaded with the action, followed by the identity contract and the failure condition. No filler or restated title.

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?

No output schema exists, yet the description effectively communicates the key return concept (instance_id) and the mode in which creation fails. A brief note on how instances persist or must later be closed via close_instance/stop_browser would close the remaining gap.

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 100%, so every parameter is already documented, including the Chrome preference and proxy-credential handoff. The description's only added meaning is the cross-tool consequence of 'label' becoming the instance_id, which the schema already states in nearly identical words. Baseline 3 applies.

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?

States a specific verb and resource ("Starts a new browser instance, Chrome or Firefox, with its own profile") and distinguishes it from lifecycle siblings by noting each instance is isolated with its own profile. It also explains the naming contract that links it to the rest of the tool set: the label becomes the instance_id other tools take.

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?

Gives a clear precondition-style exclusion: it "Fails in --user-profile mode," which tells an agent when not to call it. It does not route between this and lifecycle siblings like restart_browser or stop_browser, so the alternative-selection guidance is implicit rather than explicit.

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