Skip to main content
Glama

Load a URL in the browser

browser_goto
Destructive

Loads a URL in an existing browser session and returns the final URL, title, and HTTP status. Use it to navigate pages before taking a new snapshot for clicking.

Instructions

Load a URL in a browser session. Returns the page's final URL, title and HTTP status. Any refs from an earlier browser_snapshot stop working: take a new snapshot before clicking.

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": {
      "session_id": "<session_id>",
      "url": "<url>"
    },
    "name": "browser_goto"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesThe address to load.
timeoutNoSeconds; unset, 30.
session_idYesThe session_id `browser_open` returned.
wait_untilNoHow far the page must get before this returns. Unset, 'load'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.14.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true; the description earns credit by explaining the mechanism – previously captured snapshot refs are invalidated – which is exactly the context an agent needs before a destructive navigation. It also discloses the return payload (final URL, title, HTTP status) despite having no output schema, though it says nothing about redirects beyond the final URL or about session/network failure behavior.

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?

Three short sentences, front-loaded with the action, then the return values, then the crucial caveat. No filler and the consequence of the call is placed before the recovery advice.

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?

Covers return values, the destructive side effect on snapshot refs, and the recovery step, which is what an agent needs for this navigation tool. It leaves only secondary gaps – timeout/wait_until are fully documented in schema, but timeout or navigation-failure outcomes are not described.

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 description coverage is 100%, including defaults for timeout and wait_until, so the schema already carries the parameter burden. The description adds nothing parameter-specific beyond the URL itself.

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 ("Load a URL in a browser session") plus what comes back, which differentiates it from session-lifecycle siblings like browser_open and browser_close. It does not distinguish itself from browsing/fetching siblings such as browse or fetch_raw, so sibling separation is only partial.

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?

Gives one actionable sequencing rule – take a new snapshot before clicking after a goto – which is genuine when-to-use guidance for follow-up actions. It never says when to prefer this over browse/fetch_raw or whether it can be used on a session that already has a loaded page.

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