Skip to main content
Glama

browser_open

Render JavaScript-heavy pages in headless Chrome, wait for dynamic content, and return status, title, metadata, text excerpt, link/form counts, console errors, and screenshot.

Instructions

Open a URL in a real headless Chrome tab, wait for JS, and report what is there.

Returns final URL, HTTP status, title, meta description, rendered text excerpt, link/form counts, console errors and (by default) a screenshot path. Use this for JS-heavy sites, SPAs, Cloudflare-protected pages and anything http_fetch cannot render.

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
urlYes
wait_msNo
screenshotNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does well: it discloses the rendering engine, that JS execution is awaited, that a screenshot is captured by default, and that console errors are surfaced. It omits operational constraints such as timeouts, per-page latency, or blocking/auth limitations, which matters for a network-facing browser tool.

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 tight sentences, front-loaded with the core action, followed by the return inventory and the use-case router. The output enumeration earns its space because no output schema exists to carry that information.

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?

With no output schema and no annotations, the description steps up by documenting both behavior and return fields, which is the right call. Minor gaps remain around failure modes, timeouts, and resource cost for a headless-browser launch.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate; it explains that the tool waits for JS (implying the wait_ms knob) and that a screenshot is produced 'by default' (implying the screenshot flag). It does not explain when to raise wait_ms for slow SPAs or when to disable screenshots for speed, so it only partially covers the three parameters.

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?

The description opens with a concrete verb and resource ('Open a URL in a real headless Chrome tab'), states the mechanism (wait for JS), and enumerates the exact outputs (final URL, HTTP status, title, console errors, screenshot path). It also explicitly contrasts itself with the http_fetch sibling, so an agent can differentiate it without opening either 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?

It gives an explicit routing rule: use this for JS-heavy sites, SPAs, Cloudflare-protected pages, and 'anything http_fetch cannot render.' That names the alternative and the condition that selects it, which is exactly the guidance needed to choose between the two browser-vs-fetch tools.

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