Skip to main content
Glama
Sign In

Emailchaser

by com.emailchaser
OverviewDiscussionsAdmin

Autopilot: kill a run

kill_autopilot_run
DestructiveIdempotent

Engages the kill switch: the run halts wherever it is and can NEVER be resumed, and any campaign the run launched is paused so nothing more sends. A paused run can be resumed later; a killed one cannot. The optional reason is recorded in the run's audit trail.

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": {
      "id": "<id>"
    },
    "name": "kill_autopilot_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe numeric autopilot run ID (from list_autopilot_runs)
reasonNoWhy the run is being killed, for the audit trail

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, yet the description adds the specific consequences those hints cannot convey: the halt is irreversible, and any campaign the run launched is paused so nothing more sends. It also notes the reason is persisted to the run's audit trail, covering side effects and record-keeping beyond the schema.

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?

Three tight sentences, front-loaded with the irreversible-halt consequence, then the campaign side effect, then the optional parameter. Nothing repeats the title or wastes a clause.

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 description supplies the irreversibility warning, collateral effect on launched campaigns, and audit-trail behavior. Nothing an agent needs before invoking it destructively 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 100%, so both 'id' (numeric run ID from list_autopilot_runs) and 'reason' (why, for the audit trail) are already documented. The description restates that the reason lands in the audit trail but adds no new format, sourcing, or constraint details, so the baseline 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 action and resource ('Engages the kill switch: the run halts wherever it is') and immediately distinguishes the outcome from a mere pause by declaring it can NEVER be resumed. An agent can separate this from pause_autopilot_run or resume_autopilot_run purely on the description.

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?

The line 'A paused run can be resumed later; a killed one cannot' gives an explicit selection criterion between the destructive and non-destructive paths, which is exactly the decision an agent faces among the autopilot siblings. It stops short of naming pause_autopilot_run directly as the alternative, so it is clear rather than fully prescriptive.

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

All Emailchaser toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources