Skip to main content
Glama

browser_launch

Launch a dedicated Edge browser with remote debugging enabled and return its port, PID, and profile directory; reuse the profile directory to preserve cookies across scripts.

Instructions

Launch a dedicated Edge with --remote-debugging-port=PORT. Returns {port, pid, profile_dir}. Reuse --profile-dir to keep cookies across scripts.

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_launch"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoabout:blank
portNo
seedNo
backendNoedge = persistent cookies (default); lightpanda = WSL2+Docker, ~123 MB RAM, no persistent profile.edge
dry_runNo
headlessNo
profile_dirNoreuse a temp profile dir to keep cookies

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.3/5.0
Behavior3/5

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

With zero annotations the description carries the full burden; it does disclose the return shape and that the profile dir persists cookies, which is real added context. But it is silent on the most consequential behavior: dry_run defaults to true, so the tool may not actually start a browser, and nothing says whether the launched process lingers or needs cleanup.

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 short sentences, capability and return value front-loaded, with the persistence tip last. No filler or restatement of the name.

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 7-parameter process-spawning tool with no annotations and no output schema, the description gives the return shape but omits process lifecycle, what dry_run and seed actually change, and whether the browser must be torn down. Adequate to start, insufficient to call with confidence on non-default flags.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 29% across 7 parameters, so the description must compensate and largely does not. It touches only port (implicitly, via the flag string) and profile_dir (restating the schema's own "keep cookies" note), leaving url, seed, headless, backend, and especially dry_run without added meaning.

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 concrete verb and resource ("Launch a dedicated Edge with --remote-debugging-port=PORT") and names the return triple {port, pid, profile_dir}. An agent can distinguish this from browser_click/browser_scan/browser_shot without opening the schema, though no sibling is named explicitly.

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?

The cookie-persistence tip ("Reuse --profile-dir to keep cookies across scripts") is a genuine usage hint, and pairing with the port-returning behavior is a useful workflow cue. However there is no when-not guidance, no mention of when to prefer this over the backend=lightpanda path, and no prerequisite/lifecycle context.

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