Skip to main content
Glama

Disconnect sign-in email domain

appAuthEmailDisconnect
DestructiveIdempotent

Take an app’s own domain off its sign-in mail and put it back on Tofu’s sending address, for one owned app. Requires confirmed: true, representing the human’s agreement to disconnect auth email for this exact projectId. It reads the sending identity FIRST, then removes the records it could name, then removes the identity — because the identity is the only description of its own three DKIM records. When that first read carried no DKIM tokens it says so plainly (dns.note) and names the three records it could, rather than presenting a partial removal as a complete one. A removal Tofu cannot confirm is reported as not removed, never as done. The app keeps working throughout: its mail goes back out from Tofu’s address in the same call.

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": "appAuthEmailDisconnect"
  }
}

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
Behavior5/5

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

The annotations already declare destructive=true, idempotent=true and openWorldHint=true, but the description goes well past them: it discloses the read-then-remove ordering, why the identity must be removed last (it is the only description of its own three DKIM records), and that partial removal is surfaced via `dns.note` rather than misreported as complete. It also states a removal that cannot be confirmed is reported as not removed, and that mail keeps flowing from Tofu's address within the same call — none of which the annotations convey.

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?

The action and its scope are front-loaded, and the following sentences each add a distinct behavioral fact (precondition, ordering rationale, partial-failure reporting, continuity of mail). The parenthetical explanation of why the identity is removed last is slightly internal-facing but still justifies an ordering constraint the agent might otherwise question.

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?

With an output schema present, return shape need not be explained, and the description still covers the precondition, the destructive scope, failure/partial-removal semantics, and the fact that app mail continues working. Nothing an agent needs in order to call this safely and interpret the outcome 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 carries the burden; it explains `confirmed` as the human's explicit agreement to disconnect auth email for this specific projectId, which is meaningfully more than the `const: true` in the schema. `projectId` is only indirectly covered via 'for one owned app', leaving its identification requirement to the uuid format in the schema.

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 description states a concrete verb and resource ('take an app's own domain off its sign-in mail and put it back on Tofu's sending address') and scopes it to 'one owned app', which makes the inverse relationship to a connect operation obvious. It stops short of naming the sibling it complements, so the differentiation is inferred rather than stated.

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?

It gives a real precondition — `confirmed: true` standing for a human's agreement to disconnect auth email for this exact projectId — which tells the agent what must be true before calling. It never says when to prefer this over alternatives such as the connect or status tools, nor when not to call it, so usage is implied rather than guided.

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