Skip to main content
Glama

Connect sign-in email domain

appAuthEmailConnect

Run ONE connect pass for one owned app’s auth email — the dashboard’s own button. Requires confirmed: true, representing the human’s agreement to connect auth email for this exact projectId. It performs the single step the email provider’s last answer calls for: create the sending identity for send.<domain> if none exists, write the six records the identity names (into the customer’s own zone through the approval they gave at their DNS provider, or into a zone Tofu serves, else report them to be published by hand), or switch the app’s sending address once the provider says the domain is verified. It never writes half a configuration and never claims a step it could not confirm — a failure result does not establish that the change was applied. Repeat calls are safe: every step is idempotent at the provider, and the records it cannot write are returned for a human. It needs the app to be deployed and to have its own database.

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>",
      "confirmed": "<confirmed>"
    },
    "name": "appAuthEmailConnect"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
dnsYes
stateYes
domainYes
senderYes
appNameYes
enabledYes
messageYes
recordsYes
siteUrlYes
identityYes
nextStepsYes
observedSenderYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations it discloses genuinely useful behavior: it is a single-step state-machine advance keyed to the provider's last answer, it 'never writes half a configuration', a failure result does not prove the change was applied, and some DNS records cannot be written and are returned for manual publication. One tension: annotations set idempotentHint=false while the text says 'Repeat calls are safe: every step is idempotent at the provider', which an agent could read as 'no additional effect on repeat' even though a later call advances the next step.

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 core action is front-loaded, but the middle sentence is a ~90-word run-on with nested parentheticals and em-dashes that must be re-read to parse the three branches. The content is nearly all relevant, yet the packaging makes it dense for an agent scanning for a single decision.

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

Completeness3/5

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

An output schema exists, so return-value explanation is rightly omitted, and prerequisites plus failure semantics are covered. What is not resolved is the operational loop: the description says it acts on 'the email provider's last answer' without saying how an agent learns that answer or when to re-invoke versus check appAuthEmailStatus, and it does not say what the agent should do with records returned for human publication.

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 description coverage is 0%, so the description must carry the load and largely does: it explains that `confirmed` encodes the human's agreement for this specific connection and that `projectId` identifies 'this exact projectId' the agreement covers, which is the critical safety nuance the bare uuid schema cannot convey. It does not describe the uuid format or what happens if the project is not owned or not deployed beyond the stated prerequisite.

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?

The description opens with a specific verb and bounded scope: 'Run ONE connect pass for one owned app's auth email'. It then enumerates the three concrete outcomes (create the sending identity for `send.<domain>`, write the six named records or return them for manual publication, or switch the sending address after verification), which separates it cleanly from appAuthEmailStatus, appAuthEmailDisconnect and appAuthConfigure.

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 states when the tool is appropriate ('the dashboard's own button'), the gating prerequisite for invocation ('Requires `confirmed: true`, representing the human's agreement'), and the environmental preconditions ('the app to be deployed and to have its own database'). It stops short of explicitly naming a sibling to call first (e.g. appAuthEmailStatus to read the provider's last answer) or a condition under which an agent should not call it, so it is clear context without full routing.

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