Skip to main content
Glama

Stop Tofu adding DNS settings

domainAuthorizationRevoke
DestructiveIdempotent

Withdraw the one-click DNS authorization for a hostname — Stop Tofu adding settings on the dashboard’s Domains page. This changes what the user sees, and requires confirmed: true, representing the human’s agreement to withdraw this exact authorization; without the literal nothing is sent. Tofu stops writing records for it (those it wrote stay), destroys its stored copy of the provider’s approval and asks the provider to release it; the connection stays in place (domainRelease removes it). The result never carries a credential. A withdrawal alone never means the token is gone; providerGrant says: released, the provider confirmed; not_held, no token of Tofu’s is stored there; not_released, the approval may still be live there, and message names the step that removes it. Withdrawing again reads back the first withdrawal’s record, so an unconfirmed grant stays not_released.

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": "domainAuthorizationRevoke"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainIdYes
confirmedYes
projectIdYes

Output Schema

NameRequiredDescriptionDefault
messageYes
revokedYes
providerGrantYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations (destructiveHint=true, idempotentHint=true, openWorldHint=true) by stating exactly what is destroyed — Tofu's stored copy of the provider approval — and what survives (already-written records, the connection itself). It discloses that the result never carries a credential and decodes the providerGrant outcomes (`released`, `not_held`, `not_released`), which is real behavioral context not derivable from 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.

Conciseness4/5

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

Front-loaded with purpose and effect, and most sentences carry distinct information (what stays, what dies, what the status means). It is dense to the point of being hard to parse in places — 'without the literal nothing is sent' reads as a truncated reference to `true` — which costs a point.

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?

Despite an existing output schema, the description supplies the interpretation an agent needs to judge success (providerGrant values, the meaning of `message`). Combined with the confirmation gate and the consequences of withdrawing, nothing essential for calling this destructive tool correctly is missing.

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 the load. It explains `confirmed` well and ties it to human agreement, and 'for a hostname' hints at domainId, but projectId is never mentioned and domainId's scope is left to inference. Partial compensation only.

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?

States a specific verb and resource: 'Withdraw the one-click DNS authorization for a hostname,' with the concrete user-visible effect on the Domains page. It explicitly separates itself from the sibling domainRelease ('the connection stays in place (domainRelease removes it)'), so an agent can discriminate without opening either schema.

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

Usage Guidelines5/5

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

Gives the condition for use, the hard prerequisite ('requires `confirmed: true`, representing the human's agreement to withdraw this exact authorization; without the literal nothing is sent'), and names the alternative that removes the connection instead. It also explains repeat-invocation behavior, so an agent knows what a second call means.

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