Skip to main content
Glama

restart_browser

Restarts a browser instance and closes its open tabs, optionally applying a new proxy or WebGL preset. Use it to reset a server-launched browser; attached browsers cannot be restarted.

Instructions

Restarts an instance's browser (closing its tabs), optionally with another proxy or presets. A browser the server attached to (not launched) is not restarted: the call fails saying so.

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": "restart_browser"
  }
}

Input Schema

NameRequiredDescriptionDefault
featuresNoPresets for the new process: WEBGL_SOFTWARE (software WebGL, for GPU-less hosts). Default: none.
instance_idNoDefault: 'default'.
proxy_serverNoProxy URL; credentials go to enable_proxy_auth. Default: the instance's current proxy.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0-rc.1

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the destructive side effect (tabs are closed), the failure mode for attached browsers, and the optional proxy/preset overrides for the new process. It omits what happens to the instance itself and any auth requirements, so it stops short of full behavioral disclosure.

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?

Two compact sentences, front-loaded with the action and its side effect, with the caveat second. Nothing is wasted, though the second sentence's phrasing ('the call fails saying so') is slightly informal.

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 three-optional-parameter mutation tool with no annotations and no output schema, the description covers the key risks: tab closure, the attached-browser failure case, and the override options. Only the post-restart state of the instance and the return value are left unspecified.

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 the schema already documents all three parameters including defaults and the enable_proxy_auth pointer. The description only loosely restates that a proxy or presets can be supplied, adding no syntax or format detail beyond the schema.

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 ('Restarts an instance's browser') and adds scope detail ('closing its tabs'), so the agent knows this is a full browser restart, not a page reload. It does not name a sibling such as stop_browser or reload to contrast against, which keeps it below a 5.

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?

It gives a clear 'when it won't work' condition (a server-attached browser is not restarted and the call fails), which is genuine exclusion guidance. However, it never says when to choose this over stop_browser, reload, or open_instance, leaving the primary selection decision implicit.

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