Skip to main content
Glama

create_playbook

Create or update NowAIKit playbooks with ordered tool-call steps, enabling repeatable multi-step ServiceNow workflows that can be run later.

Instructions

Create (or update) a NowAIKit playbook definition with ordered steps that chain tool calls, stored as system property nowaikit.playbook.; run it with execute_playbook (requires NOW_ASSIST_ENABLED + WRITE_ENABLED)

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>",
      "description": "<description>",
      "steps": "<steps>"
    },
    "name": "create_playbook"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesPlaybook name
stepsYesOrdered list of playbook steps
descriptionYesPlaybook description

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv4.9.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly=false, openWorld=true, destructive=false, idempotent=false. The description adds genuinely new behavior: upsert semantics by name, the exact storage location as a system property, and the environment flags required. Minor tension between 'or update' and idempotentHint=false, but not a contradiction since upsert-by-name does not imply idempotent side effects.

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?

A single dense sentence with the primary action front-loaded and the alternative and prerequisites trailing after a semicolon. Efficient, though the packed multi-clause structure (upsert, storage path, execution pointer, env flags) takes a careful read.

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 3-parameter authoring tool with full schema coverage, annotations, and no output schema, the description supplies what the schema cannot: persistence location, the required environment flags, and the follow-up tool to run the playbook. Return behavior is not described, but no output schema exists and the effect is a stored property.

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% and already documents name, description, steps, on_error enum, condition, tool_name, and the {{context.key}} / {{steps[N].result.key}} templating. The description only alludes to 'ordered steps that chain tool calls', adding no syntax or constraint detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb+resource ('Create (or update) a NowAIKit playbook definition with ordered steps') plus the mechanism (steps chain tool calls) and the persistence target ('stored as system property nowaikit.playbook.<name>'). It also names the sibling that executes the artifact, so the agent can distinguish authoring from running without opening either 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?

Explicitly routes execution to execute_playbook and communicates the gating flags (NOW_ASSIST_ENABLED + WRITE_ENABLED) that must be on. It also clarifies this doubles as an update path. No explicit when-not-to-use case, 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