Skip to main content
Glama
Cutover MCP

Cutover MCP

Official
by gocutover

Add Task To Runbook

add_task_to_runbook

Add a new task to an existing runbook, specifying its name, level, duration, assignees, predecessors, and task type so it slots into the runbook sequence correctly.

Instructions

Add a new task to an existing runbook.

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": {
      "runbook_id": "<runbook_id>",
      "name": "<name>"
    },
    "name": "add_task_to_runbook"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe name of the new task.
levelNoThe task's level (default level_3).
messageNoFor an Email/SMS/Call comms task type, the message body. For an agentic task type, the initial prompt: the instructions the AI agent receives when the task starts. Always set it for comms and agentic tasks; if the user did not supply one, draft it from the task name, description and the runbook context.
durationNoPlanned duration in seconds.
assigneesNoList of assignees to add to the task. Only users and teams that are already participants on the runbook can be assigned; non-participants are silently ignored by the API.
end_fixedNoISO 8601 timestamp fixing the task's end time.
stream_idNoThe ID of the stream to assign the task to (can be a substream).
auto_startNoWhether the task should start automatically once its predecessors complete.
recipientsNoList of recipients for a comms task (Email/SMS/Call).
runbook_idYesThe ID of the runbook to add the task to.
task_linksNoLinks from this task to other resources. Use ``link_type="runbook"`` to link a task to a template runbook — the target must be a template and must have ≥1 task, and the task's ``task_type_id`` must be the tenant's ``linked`` task type (from ``list_task_types``, the entry with ``key == "linked"``) or the link is silently dropped. If the parent runbook isn't a template, the response's ``task_links[].id`` references a freshly-spawned copy of the template, not the template itself, and the task's name is overwritten with the target's name. Use ``link_type="snippet"`` to attach one or more snippets.
auto_finishNoWhether the task should complete automatically once started.
descriptionNoAn optional description for the task.
start_fixedNoISO 8601 timestamp fixing the task's start time.
predecessorsNoA list of task IDs that are predecessors to this task.
task_type_idNoTask type ID from ``list_task_types``, which also lists integration-backed types (Jenkins, ServiceNow, custom integrations, AI agent tasks, ...); never ask the user for the id.
custom_field_valuesNoCustom field values to set. Identify each field by custom_field_id, using the id returned by list_custom_fields with scope="task": {"custom_field_id": "123", "value": ...}. A field's internal ``name`` can be used instead of the id, but its ``display_name`` cannot. For select_menu and radiobox fields, pass the option name; for checkboxes, pass a list of option names. Pass "" to clear a field. If the API reports 'Custom field "" was not found' for a valid id, the field is most likely not available for the task's type. Values in the response are listed by ``name``, with custom_field_id set to null.

Output Schema

NameRequiredDescriptionDefault
dataYes
includedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.8/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden, yet it says nothing beyond the one-line purpose. It omits that assignees must already be runbook participants (silently ignored otherwise), that link targets must be templates, and what the response contains -- all of which live only in the parameter schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is front-loaded and free of waste, but for a 17-parameter creation tool it is under-specified rather than genuinely concise. It does not highlight the two required parameters (runbook_id, name) or the common gotchas.

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?

This is a complex 17-parameter mutation tool with no annotations; an output schema exists, so return values need not be explained, but the description should still flag required inputs, participant constraints, and the silent-drop behaviors that an agent will otherwise miss.

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 description coverage is 100%, so all 17 parameters are documented in the schema with substantial detail, including the linked-task-type and custom-field rules. The description adds nothing beyond that, so the baseline 3 applies.

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: "Add a new task to an existing runbook." An agent can tell this creates a task rather than mutating one, and the sibling update_runbook_task is implied as different, though the description never names it explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites (e.g. the runbook must exist and be editable), and no pointer to alternatives such as update_runbook_task for modifying an existing task.

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