Skip to main content
Glama

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 CrewNest it covers these actions: List customers, Update customer, Create customer, Import customers, Manage service address, Measure property, List jobs, Schedule job, List calendar, Reschedule job, Assign job, Configure recurring job, Update job status, Cancel job, Optimize route, Update job notes, Attach job photo, List estimates, Create estimate, Edit estimate, Send estimate, List invoices, Create invoice, Edit invoice, Send invoice, Record payment, Get payment link, Export invoices, Get receivables report, Configure invoice reminders, List crew, Manage team member, Invite team member, List activity, Manage message template, Configure online booking, Set default tax rate, Pause recurring job, Review team request, Get referral code, Bulk assign jobs, Claim job, Schedule recurring visit, End recurring service, Reorder route, Generate customer portal link, Review booking request, Get dashboard, List recurring services, Get job completion report, Get estimate conversion report, List measurement history, Generate referral code, Configure referral rewards, Download estimate pdf, Remind estimate, List document approvals, Review document approvals, Send payment receipt, List message history, Configure review requests, Update business settings, Configure estimate defaults, Set notification preferences, Remove team member, Regenerate team invitation, Set technician visibility, Transfer business ownership, Get payment setup status, Manage payment connection, Open payout dashboard, Get subscription, Manage subscription, Read customer portal, Pay customer invoice, Respond to estimate, Submit booking request, Confirm job assignment.

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

NameRequiredDescriptionDefault
appNoThe app's name or Cotlet slug. Default: CrewNest.
taskNoWhat the user wants done in the app, in their words.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new facts beyond that: "Free, no browser session," which tells the agent there is no cost or session side effect. It says nothing about token size, latency, or why the huge action list is returned, leaving a meaningful gap for its size.

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

Conciseness2/5

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

The first two sentences are well front-loaded and earn their place, but they are followed by roughly 80 comma-separated CrewNest action names that are unstructured, ungrouped, and far out of proportion to what an agent needs to decide whether to call the tool. The list dominates the description and obscures the operating instructions.

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 free, read-only guidance tool with no output schema, the description covers the essentials: what it returns (browser choice, sign-in link, method, screens, menus, actions, notes), when to call it, cost, and catalog-vs-generic handling. A hint about output size or how the returned guidance should be applied would close the remaining gap.

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 (app, task) are fully documented in the schema, so the baseline is 3. The description corroborates that the app may be any web app and that the task is what the user wants done in their words, but adds no syntax, default behavior, or fallback detail beyond the schema's "Default: CrewNest."

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 opens with a specific verb and resource: explains how to work in an app by clicking in the user's Cloud Browser with Cotlet's browser tools, and enumerates the payload (browser choice, sign-in link, step-by-step method, screens, menus, actions, notes, dedicated tools). It is clearly a guidance tool rather than an action tool, which separates it from the cotlet_browser_* primitives, 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 Guidelines4/5

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

"Call it before the first browser step in an app" gives an explicit call-timing rule, and "Works for any web app; one outside Cotlet's catalog gets the general method" defines the coverage boundary. It stops short of stating when NOT to call it (e.g., after the first step, or instead of cotlet_apps for pure catalog lookup).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources