Skip to main content
Glama

browser_open

Opens a URL in a named tab group within an existing browser window, leaving the new tab unselected by default so agents can load pages in the background.

Instructions

Open a URL in a named group in an existing window. Does not select the new tab by default.

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
activeNo
browserNoBrowser id from browser_list, or chrome/firefox when only one instance matches.
sessionNameNoNamed task group. Defaults to MCP Automation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations supplied, the description carries the full behavioral burden and mostly does not. It discloses only that the new tab is not selected by default — a fact already encoded in the schema's active default of false — and says nothing about prerequisites (a browser must already be running), what happens if the URL fails or the group does not exist, or whether existing tabs are reused.

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 short sentences with the scope constraint front-loaded and zero filler. It is efficient, though the brevity edges toward under-specification for a four-parameter mutation tool.

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

Completeness2/5

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

A no-annotation tool with 50% parameter coverage and no output schema needs more than this. It omits error handling, tab-group creation semantics, and the fact that the returned tab must be focused separately, which is the single most likely follow-up mistake an agent would make.

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 50%: browser and sessionName are documented in the schema, while url and active are not. The description adds modest meaning by glossing 'named group' for sessionName and clarifying the non-selection default behind active, but it leaves the url format and the precise effect of active=true unexplained.

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 object: 'Open a URL in a named group in an existing window.' That is concrete enough to distinguish it from click/fill/tab-manipulation siblings, though it never names a contrasting sibling such as browser_navigate or browser_tabs to pin down the boundary.

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?

Usage is only implied via the 'in an existing window' precondition; there is no explicit statement of when to use this rather than browser_navigate, and no note on what to do if no window exists. The 'does not select the new tab by default' clause hints at the follow-up need to focus the tab, but stops short of saying so.

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