Skip to main content
Glama

Ask DNS provider for access

domainAuthorize

Ask the DNS provider to write this connection’s records instead of the human copying them. Requires the connection’s domainId. The returned url opens an approval flow for the human. It first checks that the signed-in Tofu account owns this project, then uses the provider’s own approval screen; another account is refused. Tofu never asks for an API key, token or client secret; this tool has no credential input field. Only providers Tofu has configured can be started; an unavailable one is refused with the reason. It writes nothing by itself, and it does not buy or transfer a domain.

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>",
      "provider": "<provider>"
    },
    "name": "domainAuthorize"
  }
}

Input Schema

NameRequiredDescriptionDefault
zoneNo
domainIdYes
providerYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
idYes
urlYes
zoneYes
statusYes
messageYes
providerYes
createdAtYes
expiresAtYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations supply the safety profile (readOnly=false, destructive=false, openWorld=true, idempotent=false), and the description adds substantial context beyond them: the ownership pre-check, refusal of other accounts, no credentials/API keys involved, refusal of unconfigured providers, and the explicit scope limit that it does not buy or transfer a domain. Missing only things like what happens on repeat invocation or who must complete the approval flow and its expiry.

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

Conciseness5/5

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

Front-loaded with the outcome, then preconditions, then scope limits; short declarative sentences with no filler. The credentials sentence is mildly redundant with 'writes nothing by itself' but it preempts a likely agent mistake, so it earns its place.

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 multi-party OAuth-style authorization kickoff, the description covers purpose, preconditions, return value guidance (an approval `url`, with an output schema present), and explicit non-goals. It is only incomplete on the `zone` parameter and on pointing to the status/revoke siblings that complete the flow.

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 carries the burden. It explains `domainId` and effectively explains the `provider` constraint (only Tofu-configured providers can start), but `projectId` and especially the optional free-form `zone` (1-253 chars) are never mentioned, leaving half the inputs to be inferred from names alone.

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?

States a specific verb and resource: asking the DNS provider to write the connection's records, versus a human copying them, and names the artifact returned (an approval `url`). It is clearly distinguishable from neighbors like domainConnect or domainVerify in behavior, though it never names a sibling explicitly.

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?

Gives real preconditions (requires `domainId`, caller must own the project, provider must be Tofu-configured) and refusal cases, which is more than most. However it never routes the agent between this and the obvious siblings for the same lifecycle (domainAuthorizationStatus, domainAuthorizationRevoke, domainGuidance), so when-to-use versus alternatives is only implied.

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