Skip to main content
Glama

Open URL

browser_open

Open a URL in a shared browser and return a compact summary with URL, title, page text, and first elements to guide navigation and element actions.

Instructions

Open a URL in the shared browser and return a compact summary (URL, title, ~1500 chars of text, first elements). Free — no model call. Call this before browser_act/browser_run unless a page is already open or you pass url to browser_run. Refs from this summary are valid until the page changes; use browser_observe for the element window or browser_find to locate specific elements.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "browser_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesAbsolute URL, or a host like example.com (https:// assumed).
headedNoLaunch a visible window. Only applies before the browser first launches; set it on your first call if you want to watch.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
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 cost ('Free — no model call'), what the response contains, and a critical state rule that refs are valid only until the page changes. It stops short of failure behavior — navigation errors, timeouts, or whether a failed open leaves the previous page intact.

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 and return shape are front-loaded, then guidance, then ref lifetime — a sensible order with no filler sentences. It is dense with parenthetical asides and reads slightly like a run-on, but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, yet the description specifies the return payload and the lifetime of the refs it yields, which is exactly the context an agent needs to chain into browser_act or browser_observe. Ordering rules cover the remaining ambiguity for a simple two-parameter tool.

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% and both parameters are documented there, including the launch-once caveat for `headed`. The description adds nothing about parameter meaning beyond mentioning that `url` can alternatively be passed to browser_run, so the 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 ('Open a URL in the shared browser') and immediately defines the payload returned ('compact summary (URL, title, ~1500 chars of text, first elements)'). That return-shape detail is what separates it from browser_run and browser_observe, so an agent can choose without opening another schema.

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

Usage Guidelines5/5

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

Gives an explicit ordering rule ('Call this before browser_act/browser_run') plus two named exceptions (a page is already open, or you pass `url` to browser_run). It also routes onward: browser_observe for the element window, browser_find for locating specific elements.

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