Skip to main content
Glama

TLDMath

by com.tldmath
OverviewDiscussionsAdmin

Plan DNS setup for a domain

plan_dns_setup
Read-onlyIdempotent

The DNS records a domain needs for a website host or AI app builder (Lovable, Bolt, v0, Replit, Base44, Framer, Webflow, Bubble), an inbox provider, and/or the service an app sends email through (SPF, DKIM, DMARC), each checked against live public DNS (in place, missing, or needs change), plus where the domain’s DNS is hosted and records to remove. SPF records from different providers are merged into one. Read-only: it never changes DNS. Use after the user buys a domain, or when their site or email on a custom domain isn’t working.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hostNoWhere the website is built or hosted (an AI app builder like lovable or bolt, or a host like vercel).
emailNoInbox provider for people, or "no-email" to lock the domain against spoofing.
domainYesThe domain, e.g. "acme.dev".
senderNoTransactional email service the app sends through (sign-in links, receipts).
host_targetNoNetlify site (x.netlify.app), GitHub user, or Cloudflare Pages project (x.pages.dev), when the host needs one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / email / description
      Previous value: -"Email provider, or \"no-email\" to lock the domain against spoofing."New value: +"Inbox provider for people, or \"no-email\" to lock the domain against spoofing."
    • changedInput schema / properties / host / description
      Previous value: -"Where the website is hosted."New value: +"Where the website is built or hosted (an AI app builder like lovable or bolt, or a host like vercel)."
    • changedInput schema / properties / host / enum
      Previous value: -[
-  "vercel",
-  "netlify",
-  "github-pages",
-  "cloudflare-pages"
-]New value: +[
+  "lovable",
+  "bolt",
+  "v0",
+  "replit",
+  "base44",
+  "framer",
+  "webflow",
+  "bubble",
+  "vercel",
+  "netlify",
+  "github-pages",
+  "cloudflare-pages"
+]
    • addedInput schema / properties / sender
      Added value: +{
+  "description": "Transactional email service the app sends through (sign-in links, receipts).",
+  "enum": [
+    "resend",
+    "postmark",
+    "amazon-ses",
+    "sendgrid",
+    "mailgun",
+    "mailersend"
+  ],
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / email / enum
      Previous value: -[
-  "google-workspace",
-  "microsoft-365",
-  "zoho-mail",
-  "fastmail",
-  "proton-mail",
-  "icloud",
-  "cloudflare-email",
-  "no-email"
-]New value: +[
+  "google-workspace",
+  "microsoft-365",
+  "zoho-mail",
+  "fastmail",
+  "proton-mail",
+  "icloud",
+  "purelymail",
+  "migadu",
+  "namecheap-email",
+  "hostinger-email",
+  "cloudflare-email",
+  "no-email"
+]
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description reinforces 'Read-only: it never changes DNS.' It adds useful behavioral context beyond annotations: live public DNS checking, status categories (in place/missing/needs change), SPF merging, and identifying records to remove. No contradiction.

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 description is information-dense and covers all key points in a single structured sentence. The read-only statement is slightly redundant with annotations but harmless. Overall it is appropriately sized and front-loaded with the main purpose.

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 provides a high-level account of what the tool returns: record statuses, DNS hosting location, and records to remove. It also covers use cases, parameter interplay, and read-only behavior, making it complete enough for correct invocation.

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. The description adds helpful context about how host, email, and sender parameters relate to DNS record types and SPF merging, but it does not add syntax-level detail beyond what the schema already 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?

The description uses a specific verb ('Plan') and a clear resource ('DNS setup for a domain'), then enumerates exactly what the tool covers: website hosts, inbox providers, email-sending services, SPF/DKIM/DMARC, live DNS checks, and record statuses. This clearly distinguishes it from sibling domain-search and comparison tools.

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?

The description explicitly states when to use the tool: 'Use after the user buys a domain, or when their site or email on a custom domain isn't working.' It does not name when-not-to-use or alternative tools, but the context is clear enough for an agent to decide.

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

All TLDMath toolsInspect
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