Skip to main content
Glama
Sign In
agent-browser

agent-browser

by EgiStr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

browser_start

Start a long-lived Chrome session on the agent profile, headless by default, to give AI agents a persistent signed-in browser for automation.

Instructions

Start the long-lived agent Chrome (headless by default) on the agent profile.

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_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
headfulNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description does carry real weight: it discloses headless-by-default behavior, that the instance is long-lived (persists across calls), and that it runs on the agent profile. It does not disclose idempotency, behavior when a session already exists, or whether startup requires authentication or waits for readiness.

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?

A single sentence with no filler, front-loading the verb and resource along with the most decision-relevant detail (headless default, agent profile). Nothing to trim.

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?

An output schema exists, so return values needn't be explained, and with only one optional parameter the surface is small. The remaining gap is lifecycle semantics (repeated calls, existing session handling), which matters for a session-starting tool but is a modest omission given the schema's simplicity.

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 0% and the single 'headful' parameter has no schema description, so the description must compensate. It partially does by stating 'headless by default,' which lets an agent infer that headful inverts the default, but it never names or directly explains the parameter.

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 resource: start a long-lived agent Chrome instance on the agent profile, with the default mode noted. It reads clearly against siblings like browser_stop, browser_status, and navigate, though it never names those siblings explicitly.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance, no mention of checking browser_status first, and no statement about what happens if a browser is already running. The 'long-lived' phrasing only weakly implies this is a prerequisite to navigate/click/snapshot calls.

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

Deploy Server

Other Tools