DusterBook MCP Server and API by Cotlet

Open the browser

cotlet_browser_open

Read-only

Starts the user's Cloud Browser (a real Chrome on Cotlet, where the user is signed in to their sites) and opens url. Call it first. The URL goes to the site's open tab, else to a new tab, so the user's own tabs stay. Answers the page after it: the elements and text in view, with the same numbers. In DusterBook it serves these actions: Create quote, Schedule job, Create invoice, List booking requests, Add customer.

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": "cotlet_browser_open"
  }
}

Input Schema

Name	Required	Description	Default
`app`	No	Leave it out: the step runs in the user's web browser. Only when cotlet_app_guide names an app's own Cloud Browser, that app's slug, e.g. milanote.
`url`	No	A public http or https address, e.g. https://example.com.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already state readOnlyHint, openWorldHint, and non-idempotent behavior, so the safety profile is covered. The description adds context the annotations do not: that this is a real Chrome in which the user is signed in, and that the user's own tabs are preserved. It also discloses that the page snapshot is returned with numbered elements, which matters because there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentences are front-loaded and waste-free. The closing sentence that lists DusterBook actions ('Create quote, Schedule job, Create invoice ...') reads like cross-selling rather than operational guidance, and it dilutes the definition.

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?

With no output schema, the description correctly compensates by describing what comes back (elements and text in view with matching numbers). It covers lifecycle (call first), side effects (user's tabs stay), and authentication context (signed-in Chrome). The one gap is distinguishing this tool from navigate.

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%, so the baseline is 3, and the schema already explains both `app` (leave it out) and `url` (http or https address). The description adds the tab-targeting behavior for `url`, but nothing about the `app` slug pattern or when the app-specific browser applies.

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?

The description uses specific verbs and resources: it 'Starts the user's Cloud Browser ... and opens `url`'. That is far more than a restatement of the name 'Open the browser', and the note that it 'Answers the page after it' clarifies that the tool is not just a launcher. However, it never explains its relationship to the sibling cotlet_browser_navigate, so the agent cannot tell from the text alone when to use this tool rather than that one.

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?

'Call it first' explicitly establishes ordering relative to the other browser tools, which is the main usage question for a session-start tool. It also states the URL-targeting rule (existing tab of the site, else a new tab). It lacks explicit exclusions, such as when to use navigate after the browser is already open.

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

All DusterBook MCP Server and API by Cotlet tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?