Skip to main content
Glama

Add DNS records

domainRecordAdd
Idempotent

Add DNS records to one domain Tofu registered for the signed-in owner — Add a record, or Set up email, under Your domains → DNS records. Requires confirmed: true, representing the human’s agreement to these exact records on this exact domain; without the literal nothing is sent. Any record that is malformed or would clash — or a domain on hold because its payment was reversed (held) — refuses the whole request, with nothing sent. Otherwise Tofu first keeps a copy of the zone (snapshotId) for the dashboard’s Restore; an identical record already there answers present, so a repeat is safe. So Restore can undo a mistake, a coding agent makes at most a few changes to one domain an hour, never one that would push out a recent copy (agent_limit). It never changes or removes a record, and never one Tofu keeps. The message says what happened (after agent_limit it sends the human to the Domains page); unsure means the write outcome could not be established.

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": {
      "domain": "<domain>",
      "records": "<records>",
      "confirmed": "<confirmed>"
    },
    "name": "domainRecordAdd"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainYes
recordsYes
confirmedYes

Output Schema

NameRequiredDescriptionDefault
reasonYes
messageYes
outcomeYes
recordsYes
snapshotIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the supplied annotations: it discloses all-or-nothing validation (any malformed or clashing record, or a `held` domain, refuses the whole batch), a pre-write zone snapshot (`snapshotId`) supporting Restore, duplicate detection returning `present`, an hourly per-domain rate limit, and the `unsure` outcome when the write result is indeterminate. The claims are consistent with idempotentHint=true and destructiveHint=false rather than contradicting them.

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?

Dense but mostly front-loaded: purpose first, then the confirmation precondition, then failure and idempotency behavior, then the rate limit. Some sentences are convoluted or inverted ("So Restore can undo a mistake, a coding agent makes at most a few changes...") and the text carries visible escaping artifacts, which slightly hurts scanability but every sentence adds 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?

For a mutating, batched DNS write with an output schema present, the description covers the essentials an agent needs: confirmation gate, atomic failure, duplicate safety, rate limits, and result signaling. Remaining gaps are the record field semantics and any permission/auth requirements beyond `confirmed`.

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 0%, so the description must carry parameter meaning. It does explain `domain` (must be a domain the owner registered) and `confirmed` (human agreement to these exact records on this exact domain), but it never explains the record object's fields — host, type, answer, ttl, priority — nor defaults or constraints like minItems/maxItems, leaving the most complex part undocumented.

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 (add DNS records) plus the exact scope: one domain the signed-in owner registered with Tofu. It also draws a clear boundary against removal/editing siblings ("It never changes or removes a record"), so an agent can separate this from domainRecordDelete and domainRecords without reading their schemas.

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?

Gives concrete when-to-use framing ("Add a record, or Set up email, under Your domains → DNS records") and the hard precondition that `confirmed: true` must be present or nothing is sent. It also warns about the hourly change cap and points the human to the Domains page after `agent_limit`. It stops short of naming the sibling to call for deletion or listing, so the routing out of this tool is implied rather than explicit.

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