Boulevard MCP Server and API by Cotlet

Cotlet: how to work in an app

cotlet_app_guide

Read-onlyIdempotent

How to work in an app by clicking in the user's Cloud Browser with Cotlet's browser tools: which browser to use for this workspace and the sign-in link, the method step by step, the app's screens, menus and actions, notes, and the app's dedicated tools when Cotlet has them. Call it before the first browser step in an app. Works for any web app; one outside Cotlet's catalog gets the general method. Free, no browser session. For Boulevard it covers these actions: List appointments, Book appointment, Reschedule appointment, Book from waitlist, Add client note.

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_app_guide"
  }
}

Input Schema

Name	Required	Description	Default
`app`	No	The app's name or Cotlet slug. Default: Boulevard.
`task`	No	What the user wants done in the app, in their words.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely non-obvious behavior: 'Free, no browser session,' meaning calling it consumes no balance and does not open a browser. It also enumerates the kinds of content delivered (sign-in link, method, screens, menus, actions, notes, dedicated tools), which tells the agent what to expect back in lieu of an output schema. Minor tension: the description says it 'works for any web app' while openWorldHint=false, though this is defensible for a static catalog-driven guide.

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?

The when-to-call instruction and the free/no-session fact are packed into a compact block, with no filler sentences. It is dense to the point of crowding: the middle clause list ('the method step by step, the app's screens, menus and actions, notes...') and the trailing Boulevard action enumeration read as a run-on rather than a structured list. Still, each clause conveys routing-relevant information.

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 takes on the burden of describing returns and does so by enumerating guide contents; it also states cost and session behavior. What is missing is whether the guide must be re-fetched per task or per app, and how the returned 'dedicated tools' should be prioritized over browser steps. For a two-optional-parameter read-only guidance tool, this is nearly complete.

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 100% and both parameters are already documented (app name/slug with a Boulevard default; task in the user's words), so the schema carries the semantic load. The description adds a little meaning about the app parameter's behavior for uncatalogued apps and flags the Boulevard action set, but says nothing specific about how 'task' shapes the returned guidance. Baseline 3 is appropriate.

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 states a specific resource (an app in the user's Cloud Browser) and a specific payload: workspace's browser choice, sign-in link, step-by-step method, screens/menus/actions, notes, and the app's dedicated tools. It is clearly a guidance/instruction tool rather than an action tool, which separates it from the cotlet_browser_* siblings. It stops short of 5 because the verb phrase 'how to work in an app' is abstract and the reader must parse the following clause list to learn what is actually returned.

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?

Explicit timing is given: 'Call it before the first browser step in an app.' Coverage boundaries are also stated ('Works for any web app; one outside Cotlet's catalog gets the general method'), so the agent knows an uncatalogued app is not an error case. There is no explicit statement of when NOT to call it (e.g., if a boulevard_* dedicated tool already covers the requested action), only the hint that dedicated tools exist, so the routing against the boulevard_* siblings is left partly to inference.

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

All Boulevard 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?