Skip to main content
Glama

Connect domain

domainConnect
Idempotent

Start connecting a hostname the human owns and registered to this project. Tofu writes no DNS unless it runs a bought domain’s DNS for this app or the human approves domainAuthorize at their provider: otherwise it returns the exact records to create, whose publication requires the owner’s separate DNS authority. Off shared static hosting, a root or its www brings the other as a redirect once proven, not a second connection: the app’s own proven connection of it serves the app there instead; a never-proven claim of it adds nothing. Unless message says it already sends visitors here, or Tofu runs that DNS, the human sets its listed record in place of any parking or forwarding record; domainAuthorize never writes it. Requires a published app; without room in the account’s plan it refuses and connects nothing; a repeat returns the same connection. next.waitingOn: "tofu": nothing to create or change; oneClick: false: domainAuthorize cannot write this connection’s records.

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>",
      "hostname": "<hostname>"
    },
    "name": "domainConnect"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostnameYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
idYes
nextNo
statusYes
messageYes
hostnameYes
createdAtYes
ownershipYes
dnsRecordsYes
lastCheckedAtYes
providerVerificationYes
connectedDeploymentIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior5/5

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

The annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and the description goes well past them: it does not write DNS itself, it returns exact records to create, it requires the owner's separate DNS authority, it refuses when the plan has no room, and repeats return the same connection. It even explains the redirect relationship between a root and its www. This is substantial behavioral disclosure beyond structured fields.

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

Conciseness2/5

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

The purpose is front-loaded, but the body is a single semicolon-and-em-dash chain of roughly 180 words mingling record-creation behavior, redirect rules, plan limits, and response fields. Several clauses require re-reading to parse, and behavioral points are interleaved rather than grouped, so structure works against comprehension.

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?

An output schema exists, so return-shape explanation is not required, and the description still covers refusal conditions, idempotency, and the meaning of waitingOn/oneClick branches. It is close to complete for a two-parameter mutation, with the main shortfall being the unexplained projectId and the sheer density of the phrasing.

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

Parameters2/5

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

Schema description coverage is 0% for both parameters, so the description must carry full explanatory burden, and it largely does not. It adds semantics for hostname (a root versus its www, a never-proven claim) but says nothing about what projectId identifies or its expected form, and gives no recorded format guidance for the hostname beyond length implied by schema. The gap is significant against zero schema coverage.

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?

The opening sentence states a specific verb and resource: 'Start connecting a hostname the human owns and registered to this project.' It also marks the boundary against domainAuthorize (which it says never writes DNS on its own). The core purpose is discernible, though the heavy jargon and run-on construction obscure it for a first-time reader.

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?

It supplies real routing conditions: requires a published app, refuses without plan room, a repeat connection is safe, and it explains when domainAuthorize will not write the record. It also documents outcome branches (next.waitingOn="tofu", oneClick=false). The guidance is present but embedded in dense prose rather than cleanly sequenced, and no explicit 'use X instead when...' framing is given beyond the domainAuthorize contrast.

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