Skip to main content
Glama
Rootly MCP server

Rootly MCP server

Official
by rootlyhq

List Ai Automation Runs

list_ai_automation_runs
Read-only

List recent runs of a specific AI automation with status, trigger type, and timing to review execution history. Read-only, with filters and pagination for scanning older runs.

Instructions

List recent runs of one AI automation with status, trigger and timing. Read-only.

Scans the 1000 most recent runs matching the filters; pagination and counts cover the visible runs in that window. When meta.next_scan_cursor is set, older runs exist beyond the window. Present only on the last page of the current scan window; finish page pagination before following it. Repeat the request with filter[scan_cursor] set to that opaque cursor to continue. Incident-linked runs are visible only when the caller's role permits access. OAuth tokens also need the ir.incidents:read scope; API keys use the key's role. Requires OAuth scope ai.automations: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": {
      "ai_automation_id": "<ai_automation_id>"
    },
    "name": "list_ai_automation_runs"
  }
}

Input Schema

NameRequiredDescriptionDefault
filter_statusNoComma-separated statuses; any matching status is included.
ai_automation_idYesRequired. ID of the ai automation (fills `{ai_automation_id}` in /v1/ai/automations/{ai_automation_id}/runs).
filter_scan_cursorNoOpaque encrypted cursor from meta.next_scan_cursor.
filter_trigger_kindNoComma-separated trigger kinds; any matching kind is included.
filter_created_at_gteNo
filter_created_at_lteNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.0.0

TDQS

A4.1/5.0
Behavior5/5

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

With readOnlyHint and destructiveHint already declared, the description still adds substantial behavior: the 1000-run cap and that pagination/counts only cover the visible window, the presence/absence of meta.next_scan_cursor signalling older runs, and that incident-linked runs are filtered by caller role. It also discloses auth requirements (OAuth `ir.incidents:read` and `ai.automations:write`; API keys governed by key role), which is exactly the kind of context annotations cannot carry.

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 and organized: purpose and read-only in sentence one, then window/pagination semantics, then access control. Sentences are dense but each carries non-redundant information; the only mild overhead is that the auth information is split across two trailing sentences.

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 filtered-list tool with an output schema (so return values need not be described), the definition covers the essentials an agent needs: window limits, cursor follow-up procedure, access-scope requirements, and visibility rules for incident-linked runs. Only minor gaps remain, such as nothing on ordering of results or behavior when no filters are supplied.

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 67%, so the schema documents most parameters including filter_status and filter_trigger_kind comma syntax. The description adds meaningful semantics only for the cursor parameter (filter[scan_cursor] must hold the opaque value from meta.next_scan_cursor, used after exhausting the current window); the date-range filters and comma-multi-value behavior are left entirely to the schema.

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?

The description opens with a specific verb+resource+scope: 'List recent runs of one AI automation with status, trigger and timing,' which tells an agent it retrieves runs for a single automation rather than all automation runs. It does not name the singular sibling get_ai_automation_run to draw the list-vs-fetch distinction, so it falls short of a 5.

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?

Strong operational usage guidance: it explains the 1000-run scan window, instructs the caller to finish page pagination before following meta.next_scan_cursor, and says to repeat the request with filter[scan_cursor]. What's missing is explicit routing guidance (e.g. when to use this versus get_ai_automation_run for a single run).

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