Skip to main content
Glama
Email Sending MCP

Email Sending MCP

by resend

Cancel Automation Run

cancel-automation-run
DestructiveIdempotent

Cancel an unfinished automation run to skip its remaining steps and stop further emails from that run to the contact while other runs and the automation continue.

Instructions

Cancel one automation run that has not finished (status running or quota_exceeded). Its remaining steps are skipped, so the contact gets no further emails from this run. Other runs and the automation itself keep going; to stop new runs, disable the automation with update-automation. Before using this tool, you MUST double-check with the user that they want to cancel this run. Reference the automation NAME and the run ID when confirming, and warn the user that cancelling is irreversible. You may only use this tool if the user explicitly confirms. Cancelling a run that is already cancelled succeeds and changes nothing. Fails if the run has already completed or failed.

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": {
      "automationId": "<automationId>",
      "runId": "<runId>"
    },
    "name": "cancel-automation-run"
  }
}

Input Schema

NameRequiredDescriptionDefault
runIdYesThe ID of the run to cancel. Find it with get-automation-runs, status "running" or "quota_exceeded".
automationIdYesThe automation ID or Resend dashboard URL (e.g. https://resend.com/automations/<id>)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.28.2

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds substantive context beyond them: remaining steps are skipped, other runs and the automation continue, re-cancelling a cancelled run is a no-op, and calls fail for completed/failed runs. Only the safety profile is redundant with annotations, and even that is expanded with the irreversibility warning to surface to the user.

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 the core action and scope, then behavior, then the confirmation gate. Slightly over-long: the confirmation requirement is stated twice ("you MUST double-check with the user" and "only use this tool if the user explicitly confirms"), and the NAME/run-ID referencing rule interrupts the behavioral flow.

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?

For a two-parameter destructive mutation with no output schema, the definition covers the eligible states, side effects, non-effects on siblings, idempotent repeat behavior, and both failure conditions — everything an agent needs to act and to explain the consequence to the user.

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 coverage is 100% and both parameters are fully documented in-schema, including where to find the run ID and that automationId accepts a dashboard URL. The description adds only the confirmation-time requirement to cite the automation name alongside the run ID, not new argument semantics, so baseline 3 applies.

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 ("Cancel one automation run") plus the eligible status set (running or quota_exceeded), which distinguishes it from siblings like update-automation and cancel-broadcast without needing the 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?

Explicitly scopes the tool to individual runs and routes the different intent (stopping future runs) to update-automation with a disable action. It also names a required precondition — explicit user confirmation — so an agent knows exactly when it may not call it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools