Skip to main content
Glama

create_playbook

Create a new multi-step playbook in the user's Ballet workspace. Use when the user wants to build a reusable automation, for example a recurring report, lead enrichment flow, invoice approval, or support triage workflow. Requires collectionId from list_collections (or create_collection). Each code step needs id, language, code, input mappings, output.variable (assign that variable, never a top-level return), and sandbox (allowNetwork/secrets/packages). Authoring details are in get_builder_guide topics "playbook" and "sdk".

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

Input Schema

NameRequiredDescriptionDefault
nameYes
stepsYesCode or HTTP steps. Code steps require sandbox, input template mappings, and output.variable. See get_builder_guide topic "playbook".
descriptionNo
inputSchemaNo
collectionIdYesCollection this playbook belongs to. Required. Copy an id from list_collections, or create_collection if none fit.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4/5.0
Behavior3/5

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

Annotations already establish this as a non-read-only, non-destructive creation operation, and the description adds genuine non-obvious payload rules: code steps need sandbox, input template mappings, and output.variable rather than a top-level return. However it says nothing about what is returned, whether creation is reversible, or whether publishing/triggering is a separate follow-up step, so behavioral coverage remains partial.

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?

Purpose and usage examples are front-loaded, and the prerequisite and guide pointer are placed after them. The third sentence is dense and packs several distinct requirements together, but each clause carries real information rather than restating the name.

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

Completeness3/5

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

For a tool creating a nested multi-step object with no output schema, the definition covers the two hardest required inputs (collectionId and steps) and defers deep authoring detail to get_builder_guide topics, which is a reasonable delegation. It still leaves the inputSchema parameter and the shape of non-code steps unexplained, so an agent would likely need a follow-up guide call before calling correctly.

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?

With schema coverage at 40% and a nested steps array, the description meaningfully compensates by enumerating what each code step requires (id, language, code, input mappings, output.variable, sandbox with allowNetwork/secrets/packages) and by explaining where collectionId comes from. The top-level inputSchema parameter is left entirely unexplained in both schema and description.

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 ('Create a new multi-step playbook'), scopes it to the user's Ballet workspace, and immediately distinguishes it from modification or collection work by pointing to update-oriented and collection siblings indirectly. An agent can identify the operation without opening the 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 states explicitly when to use it ('when the user wants to build a reusable automation') and supplies four concrete example scenarios, plus the prerequisite that a collectionId must come from list_collections or create_collection. The only gap is that it never says when not to use it, e.g. that modifying an existing playbook belongs to update_playbook.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources