Skip to main content
Glama
Cutover MCP

Cutover MCP

Official
by gocutover

Create Runbook

create_runbook

Create a new runbook in a workspace or copy an existing runbook/template with tasks, teams, users, schedules, and status settings.

Instructions

Create a new runbook in a workspace, or as a copy of an existing runbook/template.

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": {
      "name": "<name>"
    },
    "name": "create_runbook"
  }
}

Input Schema

NameRequiredDescriptionDefault
rtoNoRecovery Time Objective (RTO) in seconds (optional).
nameYesThe name of the new runbook.
statusNoThe new RAG status for the runbook (Allowed: off, red, amber, green).
timezoneNoIANA Timezone name (optional).
folder_idNoID of the folder to place the new runbook in (optional, relationship field). If omitted, the runbook lands in the workspace's default location.
auto_startNoWhether to auto-start the runbook once start_scheduled is reached. Auto-started runbooks run in live mode with comms on.
copy_tasksNoWhether to copy the source's tasks. Defaults to True.
copy_teamsNoWhether to copy the source's teams. Defaults to True. Teams are copied without their members unless copy_users is also True, so keep teams and users together.
copy_usersNoWhether to copy the source's users. Defaults to True.
descriptionNoAn optional description for the runbook.
is_templateNoWhether the runbook is a template (optional, true/false).
rto_end_taskNoID of the end task for RTO/RTA feature (optional, relationship field).
workspace_idNoThe ID of the workspace to create the runbook in (relationship field). Required unless copy_source_runbook_id is passed.
end_scheduledNoISO 8601 timestamp for the runbook's scheduled end. Must be omitted if start_scheduled is not set.
template_typeNoThe template type of the runbook. Allowed values: off, default, snippet.
rto_start_taskNoID of the start task for RTO/RTA feature (optional, relationship field).
master_templateNoWhether this runbook can be used to create app-specific templates from the Workspace Data Sources view. Requires is_template=True; the API rejects setting this on a non-template runbook. Do NOT respond to that rejection by also setting is_template=True in the same or a follow-up call unless the user explicitly asked for the runbook to become a template — silently converting a live runbook into a template is a significant, hard-to-reverse side effect. Surface the rejection and ask the user instead.
runbook_type_idNoThe ID of the runbook type to associate with this runbook (optional, relationship field).
start_scheduledNoISO 8601 timestamp, or the literal string "now", to schedule the runbook's start. Mutually exclusive with a planned start time set elsewhere; the scheduler ignores times in the past.
shift_fixed_timesNoWhen copying, whether start_fixed/end_fixed task attributes should be recalculated relative to the new runbook's start.
custom_field_valuesNoCustom field values to set, including the runbook dashboard fields on the runbook homepage (e.g. Executive summary, Additional notes), the Post-Implementation Review (PIR) and the Incident Review (e.g. Incident Summary, RCA, Lessons Learned). Identify each field by custom_field_id, using the id returned by list_custom_fields with scope="runbook": {"custom_field_id": "123", "value": ...}. A field's internal ``name`` (e.g. "dashboard:incident_review:lessons_learned") can be used instead of the id, but its ``display_name`` ("Lessons Learned") cannot. For select_menu and radiobox fields, pass the option name; for checkboxes, pass a list of option names. Pass "" to clear a field. Values in the response are listed by ``name``, with custom_field_id set to null.
copy_source_runbook_idNoID of an existing runbook/template to copy from. When set, this runbook is created as a copy and workspace_id may be omitted. The copy flags below all default to a full clone; only set one to False when the user asks to exclude that part.

Output Schema

NameRequiredDescriptionDefault
dataYes
includedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden, and it does disclose the meaningful behavioral fork: a copy operation versus a fresh creation. It says nothing about required permissions, what is created by default, or irreversibility, though the schema field descriptions do cover the riskier behaviors (copy flag defaults, master_template rejection).

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?

One front-loaded sentence with zero filler; the alternative mode is stated in the same breath as the primary action. Nothing could be removed without losing meaning.

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 22-parameter tool the description is terse, but with 100% schema coverage and an output schema present, the agent has the detail it needs on parameters and return values. The remaining gap is routing guidance against sibling mutation tools, which the description does not provide.

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?

Schema description coverage is 100%, so the baseline is 3, and the description adds an extra semantic layer by signaling that copy-related parameters only matter in the copy path. It does not enumerate or explain the individually tricky parameters (start_scheduled/end_scheduled coupling, master_template/is_template dependency) in the prose itself.

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?

A specific verb plus resource ('Create a new runbook') that also names the two supported creation modes: fresh in a workspace, or as a copy of an existing runbook/template. That distinction is genuinely useful and not obvious from the name alone. It does not explicitly distinguish itself from update_runbook or manage_runbook, which keeps it at 4.

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?

The copy-vs-create split implies when each mode applies, but the description never says when to prefer this over update_runbook or manage_runbook, nor does it mention the workspace_id / copy_source_runbook_id exclusivity in prose (that lives only in the schema). Usage context is implied rather than stated.

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