Skip to main content
Glama
Sign In

Utplava

by dev.utplava.app
OverviewDiscussionsAdmin

Connect a custom domain

connect_domain
Idempotent

Connects a domain the user owns (e.g. mybakery.com or app.mybakery.com) to one of their live apps, or re-checks one already connected. Returns the status and, until it's live, the DNS records the user must add (and any old ones to take out) at their domain provider, with steps for that provider.

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": {
      "appId": "<appId>",
      "domain": "<domain>"
    },
    "name": "connect_domain"
  }
}

Input Schema

NameRequiredDescriptionDefault
appIdYes
domainYesThe domain to connect, e.g. "mybakery.com" or "app.mybakery.com".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare non-readonly, open-world, idempotent, and non-destructive behavior, so the bar is lower. The description adds meaningful context beyond that: it returns status plus required DNS records and provider-specific setup steps until live, which is important for a mutation tool with a diagnostic re-check mode.

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?

Two tightly written sentences front-load the action and follow with the return behavior. No repeated or wasted language.

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?

Given only two parameters and no output schema, the description is nearly complete: it explains both the connect and re-check paths and the DNS-record return. It could do slightly more on error or ownership-verification cases and on where appId comes from.

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 only 50%, with 'domain' described in the schema and 'appId' undocumented. The description reinforces domain ownership and examples, and 'one of their live apps' loosely ties appId to a live app, but it does not explain how to obtain or validate appId beyond what the schema format provides.

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 ('Connects a domain ... to one of their live apps') and adds a distinct second mode ('or re-checks one already connected'). The examples of root vs subdomain make the scope concrete, and no sibling tool overlaps.

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?

Clearly implies when to use it: the user owns the domain and the target app is live; if the domain is already connected, the tool re-checks it. It does not state explicit exclusions or failure cases (e.g., domain connected elsewhere), but there are no sibling alternatives to route against.

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

All Utplava toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources