Raccoon MCP

dev_pipeline_start

Destructive

Launch a persistent background DAG of pipeline nodes that runs asynchronously, with lock-based coordination and retry support for idempotent tasks.

Instructions

Start a persistent background DAG. Returns immediately. Locks coordinate pipelines in this service; use matching lock names for shared resources. Retries require idempotent nodes.

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": {
      "pipeline": "<pipeline>"
    },
    "name": "dev_pipeline_start"
  }
}

Input Schema

Name	Required	Description	Default
`deviceId`	No
`pipeline`	Yes
`deviceName`	No
`idempotencyKey`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.8.0Oct 20, 2026

TDQS

B3.3/5.0

Behavior4/5

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

Annotations only declare the safety profile (not read-only, open-world, destructive); the description adds genuinely useful behavior beyond them: the call returns immediately (async), the DAG persists in the background, lock names coordinate shared resources, and retries are only safe for idempotent nodes. It still does not explain what the destructive aspect is or how results are later retrieved.

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?

Four short sentences, each carrying a distinct operational fact, with the core behavior ('Returns immediately') front-loaded. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with a large nested schema, no output schema, and 0% parameter documentation, the description is far too thin: it omits how to observe the run (dev_pipeline_status/logs/wait), what the returned handle is, and most node configuration semantics. The runtime behavior notes help but do not cover the calling surface.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across a 4-parameter schema with a deeply nested pipeline object (nodes with dependsOn, retries, timeoutMs, capture, retryUntil, etc.). The description only touches node 'locks' and node 'idempotent'; deviceId, deviceName, idempotencyKey, pipeline.name, cwd, parallelism and the bulk of node fields are unexplained anywhere.

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?

States a specific verb and resource ('Start a persistent background DAG') that an agent can distinguish from validate/status/list/wait siblings. It does not, however, differentiate itself from dev_pipeline_resume or process_start, which also launch work.

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?

Usage is implied rather than stated: 'persistent background DAG' hints this is for fire-and-forget orchestration, and the lock/idempotency notes give modeling guidance. There is no explicit 'use this instead of X' or precondition statement against the many sibling pipeline tools.

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

Deploy Server