Skip to main content
Glama

Disconnect domain

domainRelease
DestructiveIdempotent

Disconnect a hostname, any DNS-provider approval and any root or www it brought (Domains page): requires confirmed: true, representing the human’s agreement to release this exact hostname. The app stops showing there even with the other name connected, but a bought apex’s www returns to the apex’s redirect. A never-proven claim goes alone; another connection’s redirect there stays. The owner keeps the domain. If domainOwned lists its open registration with this projectId and a dnsMode other than external, Tofu takes out the settings it added for this hostname once the connection is gone, and the owner’s own settings stay. Otherwise DNS is untouched: Tofu’s settings — the connection’s ownership, providerVerification and dnsRecords — stay there, and the address still points at Tofu until the owner deletes them; Tofu can’t, and domains stops listing them. not_released means the approval may still be live, a non-null domain no release yet; each message explains.

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": {
      "projectId": "<projectId>",
      "domainId": "<domainId>",
      "confirmed": "<confirmed>"
    },
    "name": "domainRelease"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainIdYes
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
domainYes
authorizationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior5/5

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

Goes far beyond the annotations, which only say destructive/idempotent/openWorld. It discloses what is destroyed versus retained in each branch (connection, DNS records when `domainOwned` shows an open registration with a non-`external` `dnsMode`, the owner's own settings), that the owner keeps the domain, that Tofu's records may persist and stop being listed, and what `not_released` with a non-null `domain` means on retry.

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

Conciseness3/5

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

The critical constraint is front-loaded, which is good. But the body is a dense run-on wall of jargon-heavy clauses ('a bought apex's `www` returns to the apex's redirect', 'a never-proven claim goes alone') that would benefit from being split or bulleted into the release outcome versus the retained state.

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 destructive, multi-branch operation with an output schema present, the description covers the important state transitions and failure signaling (`not_released`, per-item `message`). Remaining gaps are minor — no mention of permission/auth requirements or preconditions such as connection verification state.

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 `confirmed: true` as the human's agreement to release this exact hostname and references `projectId` in the `domainOwned` check, but `domainId` is never characterized and the two identifiers are only indirectly explained.

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?

Opens with a specific verb and resource ('Disconnect a hostname') and immediately narrows scope (DNS-provider approval plus any root/`www` it brought), so an agent can tell this apart from connect/authorize style siblings. It stops short of naming the alternative sibling explicitly, but the action and its boundary are unambiguous.

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

Usage Guidelines3/5

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

The prerequisite is stated clearly ('requires `confirmed: true`, representing the human's agreement to release this exact hostname'), which is real when-to-use guidance. However there is no explicit when-not or named alternative (e.g. revoking an authorization instead of releasing), leaving routing between destructive domain operations to inference.

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