Skip to main content
Glama

run_playbook

Destructive

Start a run of an existing Ballet playbook and return a run ID. Use when the user wants to execute a saved automation such as a weekly report, lead enrichment, invoice approval, or ticket triage. Requires a playbook ID from list_playbooks. Pass wait=true to block up to 50s for the final output; otherwise poll with get_run.

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": {
      "id": "<id>"
    },
    "name": "run_playbook"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesPlaybook ID
waitNoWhen true, block until the run completes (capped at 50s) and return the final output. When false (default), return the runId immediately for a later get_run.
inputNoInput data for the playbook

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true, and the description adds real behavioral detail: it returns a runId immediately, execution is asynchronous, blocking is capped at 50s, and polling is done through get_run. It does not explain what side effects the run has on external systems, which is the one gap left for a destructive-flagged tool.

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?

Four short sentences, front-loaded with the action and its return value, then usage, prerequisite, and mode selection. Slight redundancy with the schema on the wait flag, but no wasted 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?

With no output schema, the description correctly states what comes back (run ID, or final output when wait=true). The main shortfall is the nested 'input' object, which is left as 'Input data for the playbook' with no guidance on its expected structure.

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 100%, so the wait parameter's block-until-complete/default-false behavior is already fully documented in the schema and the description only restates it. The description does add provenance for the required 'id' (comes from list_playbooks), but says nothing about the nested 'input' object's shape or how it maps to the playbook's expected inputs.

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?

Specific verb+resource: 'Start a run of an existing Ballet playbook and return a run ID.' It also implicitly distinguishes itself from run_scratch_code by scoping to a saved/existing playbook, so an agent can pick between them without opening schemas.

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

Usage Guidelines5/5

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

It names concrete trigger scenarios (weekly report, lead enrichment, invoice approval, ticket triage), states the prerequisite ('Requires a playbook ID from list_playbooks'), and routes between the two usage modes – wait=true to block up to 50s, otherwise poll with get_run.

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