Skip to main content
Glama

Delete a DNS record

domainRecordDelete
DestructiveIdempotent

Delete ONE of the owner’s DNS records from a domain Tofu registered for them — Delete under Your domains → DNS records. Requires confirmed: true, representing the human’s agreement to delete this exact record; without the literal nothing is sent. The input identifies the record by id, host, type and answer: it is then deleted only while it is still that one (changed otherwise). This tool deletes A, AAAA, CNAME and SRV records only — never MX or TXT (dashboard_only: the human deletes those on the Domains page) — and never one Tofu keeps for the site (tofu_record). Tofu keeps a copy of the zone first (snapshotId), which the dashboard’s Restore puts back. message says what happened: a refusal changes nothing and says why; a record already gone answers absent, so repeating is safe; an unsure answer means the record may or may not be gone and says what to do before deleting it again.

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>",
      "record": "<record>",
      "confirmed": "<confirmed>"
    },
    "name": "domainRecordDelete"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainYes
recordYes
confirmedYes

Output Schema

NameRequiredDescriptionDefault
reasonYes
messageYes
outcomeYes
snapshotIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructive/openWorld/idempotent, and the description adds substantial context beyond them: the literal `confirmed: true` gate with no request sent otherwise, optimistic-concurrency matching on id/host/type/answer with `changed` on mismatch, a zone snapshot (`snapshotId`) taken first and restorable, and the refusal/`absent`/`unsure` message semantics. This is exactly the extra behavioral detail a destructive tool needs.

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?

Front-loaded with verb and scope, then preconditions, then outcome semantics — a sensible order with little waste. It is dense and slightly long, with stacked parentheticals (`dashboard_only`, `tofu_record`, `snapshotId`, `absent`, `unsure`), but nearly every clause carries information an agent needs before a destructive call.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, nested-object mutation with an output schema, the definition covers preconditions, concurrency behavior, backup/restore, and every outcome branch an agent must react to. Nothing needed to call it safely or to interpret a failure is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry the load and largely does: `confirmed` is explained as a literal human-agreement token, and the `record` sub-fields are explained as an identity tuple used to verify the record is 'still that one'. `domain` is only obliquely covered via 'a domain Tofu registered for them' — the ownership constraint is implied rather than stated as a parameter rule.

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 ('Delete ONE of the owner's DNS records') with an explicit scope limit ('ONE', only records in Your domains → DNS records). The named exclusions (never MX/TXT, never a Tofu-kept record) let an agent distinguish this from domainRecordAdd, domainRecords and the dashboard path without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Gives when-not conditions (MX/TXT are dashboard_only, Tofu's own records are off-limits) and names the alternative route (the human deletes those on the Domains page). It also explains the precondition gate — the human must have agreed to delete this exact record — and what to do on an 'unsure' answer before retrying.

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