spillway-mcp

agy_cancel

Idempotent

Cancel a running or queued Antigravity job by job ID to terminate hung child process trees and free the serialized queue so subsequent jobs are not blocked.

Instructions

Cancel a currently running or queued Antigravity job by job_id (or "active"), terminating any hung or unneeded child process tree (taskkill /T /F) and freeing the serialized agy queue immediately. WHEN TO USE: Aborting an in-flight or queued agy job shown in agy_status so subsequent calls are not blocked. DO NOT USE FOR: Read-only status checks (use agy_status or agy_job_result). RETURNS: JSON cancellation report { ok, job_id, previous_state, state, pid, elapsed_s, message } plus telemetry footer.

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": {
      "job_id": "<job_id>"
    },
    "name": "agy_cancel"
  }
}

Input Schema

Name	Required	Description	Default
`job_id`	Yes	The job_id to cancel (e.g. "job-1730250000000-a1b2c3"), or "active" / "current" to cancel the currently running job.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.3.0Oct 30, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Goes well beyond annotations: discloses force-kill semantics (`taskkill /T /F`), that the whole child process tree dies, and that the serialized agy queue is freed immediately, plus the exact return payload shape. There is mild tension with destructiveHint=false, since a forced process-tree kill is forceful, but it is a cancellation (not data destruction) and the description honestly surfaces the effect rather than hiding it.

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?

Front-loaded with the action and key, then clearly labeled WHEN TO USE / DO NOT USE / RETURNS sections. The taskkill detail and queue-freeing note both earn their place; nothing is redundant.

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 no output schema, the description supplies the return field list ({ ok, job_id, previous_state, state, pid, elapsed_s, message }) and describes the side effects on the process tree and queue. An agent has everything needed to call this correctly and interpret the result.

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 already documents the job_id format and the "active"/"current" aliases, so the description's mention of the same values adds little. Baseline 3 applies when the schema carries the parameter burden.

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 (Cancel) and resource (running or queued Antigravity job) and identifies the lookup key (job_id or "active"). It distinguishes itself from agy_status/agy_job_result in the DO NOT USE line, so an agent can route without opening schemas.

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?

Explicit WHEN TO USE (aborting an in-flight or queued job so subsequent calls are not blocked) and DO NOT USE FOR (read-only status checks, naming the two alternative tools). Both the positive and negative conditions are stated.

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

Deploy Server