Skip to main content
Glama
Rootly MCP server

Rootly MCP server

Official
by rootlyhq

Update Ai Automation

update_ai_automation
DestructiveIdempotent

Modify an existing AI automation by sending only the attributes to change. Update its prompt, triggers, allowed tools, or destination; any triggers you send replace the current ones.

Instructions

Change an existing AI automation. Only the attributes you send change; triggers, when sent, replace the automation's triggers. Changing the prompt, allowed tools or destination changes what every future run does, and the previous values are not kept. An AI automation is a saved instruction (prompt) that a Rootly AI agent runs on a schedule, on a matching event (incident, alert, Slack message, webhook) or on demand. When it runs, the agent may only use the tools listed in the automation's allowed_tool_keys (all team-allowed tools when null), and it posts its answer to the configured destination (a Slack channel or the incident timeline), or nowhere when destination_kind is none.

Requires OAuth scope ai.automations:write. Read-only attributes are ignored on write.

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>",
      "data": "<data>"
    },
    "name": "update_ai_automation"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesRequired. ID of the automation (fills `{id}` in /v1/ai/automations/{id}). Pass it as `id` -- this tool has no `automation_id` argument.
dataYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.0.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations it discloses the key destructive behavior ('the previous values are not kept'), the replace-not-merge semantics of triggers, that read-only attributes are silently ignored, and the required OAuth scope `ai.automations:write`. It also explains the runtime destination fallback and permission checks, which is exactly the kind of consequence detail an agent needs before a destructive write.

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 mutation semantics and the destructive warning before the domain explanation, which is the right ordering. The middle sentence explaining what an AI automation is runs long and could be trimmed, but it earns its place by giving an agent the mental model needed to set fields correctly.

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

Completeness4/5

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

For a destructive, nested-object update tool with an output schema, the description covers the consequential behavior (destruction, replacement, auth scope, destination side effects) well. Remaining gaps, such as idempotency and the exact response shape, are already carried by annotations and the output schema.

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

Parameters4/5

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

Although top-level schema coverage is 50%, the nested schema is densely documented, and the description still adds conceptual meaning: what changing prompt/allowed_tool_keys/destination implies going forward, the null inheritance of allowed_tool_keys, and the 'none' destination. Some fields (limits, skill_ids, cooldown details) are left entirely to the schema.

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?

The description opens with a specific verb and resource ('Change an existing AI automation') and then defines what an AI automation actually is (a saved prompt run on a schedule, event, or on demand). Combined with the naming of the sibling set, an agent can tell this apart from create_ai_automation, get_ai_automation, and run_ai_automation without opening a schema.

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?

It clearly explains the update contract: only sent attributes change, and `triggers` replaces wholesale when sent. That is strong context for when to reach for this tool versus a create, but it never explicitly names alternatives or states when-not to use it, so it falls short of a 5.

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