Skip to main content
Glama

choose_browser

Select the browser this server uses by listing available options or passing the user's chosen ID; never choose for them.

Instructions

Pick the browser this server may use. Call it without arguments to list the options, then pass the id the USER picked; never choose for them.

Options: an already-open browser with a local debug port (uses its real profile, one new tab), a detected Chromium-based browser started with this server's private profile, Playwright's bundled Chromium, or "other" with the path of another Chromium-based browser. Changing the choice closes the current session first. Nothing opens until the next tool call.

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": "choose_browser"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
choiceNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.1.0

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that changing the choice closes the current session first, that the choice only takes effect on the next tool call, and what each browser mode implies for profile and tab usage. It stops short of covering failure behavior for an invalid id or path.

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?

Front-loaded with the imperative and the no-argument listing behavior, then the option enumeration, then the state-change warning. The option list is somewhat long but each mode carries distinct information an agent would otherwise have to guess.

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-mutating tool with no annotations, the description covers the destructive side effect, the deferred activation, and the input modes. Since an output schema exists, return values need not be explained, leaving only edge-case error behavior as a gap.

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 coverage is 0%, so the description must compensate, and it largely does: it explains that the id returned from the option listing is what gets passed, and that 'other' requires the path of another Chromium-based browser. It never explicitly binds these to the parameter names 'choice' and 'path', leaving a small mapping effort for the agent.

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?

States a specific verb and resource ('Pick the browser this server may use') and immediately enumerates the selectable browser modes, which lets an agent distinguish it from siblings like close_browser and open_site without opening any 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?

Gives explicit procedural guidance: call with no arguments to list options, then pass the id the USER picked and never choose for them. It also states the ordering constraint ('Nothing opens until the next tool call'), so the when-to-use and sequencing are unambiguous.

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