Skip to main content
Glama

start_session

Starts a browser session in the user's own signed-in browser when no tab is shared, letting an agent work in a separate window or on the current tab after user approval.

Instructions

Start working in the user's own browser (their logins and cookies) when no tab is shared yet. mode=window (default) opens a separate window for you, so the user's tabs are left alone; every tab you open in it is yours. mode=current asks to use the tab the user is looking at, for tasks about the page they're on. The user approves in a prompt (up to two minutes). Returns the tab handle and a snapshot.

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": {
      "reason": "<reason>"
    },
    "name": "start_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoFor mode=window: the page to open first.
modeNo
reasonYesOne sentence the user will read, saying what you're about to do.
browserNoBrowser key when several are connected.

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 at all, the description carries the full burden and does well: it discloses the user-approval prompt with an approximate two-minute bound, that window mode leaves the user's tabs untouched and that tabs opened there belong to the agent, and that a tab handle plus snapshot is returned. It omits what happens on denial, timeout, or failed approval, which is the remaining behavioral gap.

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?

Four dense sentences, front-loaded with the primary precondition, then mode semantics, then the approval cost, then the return value. Every sentence carries information an agent needs; nothing is redundant with the title or schema alone.

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?

For a session-establishing tool with no output schema, the description covers purpose, mode selection, the human-approval latency, and the shape of the return value, which is nearly everything needed to invoke it correctly. The only missing piece is failure/timeout behavior, which matters because approval can be declined.

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?

The schema covers 75% of parameters, so the description's main added value is explaining the 'mode' enum values (window vs current), which the schema lists without per-value descriptions. It also ties 'url' to mode=window ('the page to open first'), while 'browser' is left to the schema.

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 uses a specific verb and resource ('Start working in the user's own browser') and immediately scopes it with a precondition ('when no tab is shared yet'), which distinguishes it from tab-oriented siblings like list_tabs or open_tab. An agent can tell what this tool is for without consulting the schema.

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

Usage Guidelines4/5

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

It provides clear when-to-use guidance via the 'no tab is shared yet' precondition and then routes between the two modes: window for independent work, current for tasks about the page the user is on. It stops short of naming an explicit alternative tool to use once a session already exists, but the context is unambiguous.

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