Skip to main content
Glama
Podcast MCP
by calebn

pipeline_run

Run the production pipeline to process podcast projects with optional step/config overrides, transcript reuse or forced transcription/retiming, and shared Studio working-set syncing.

Instructions

Run the production pipeline. Optional skip_steps (step names) / config (object) override yaml.

When use_working_set is true (default), also reads/writes the GUI session working set so agents and ShareCut Studio share the same visible config. Omit unattended to leave the working-set Batch mode unchanged. Existing transcripts are reused; force_transcribe=true re-runs ASR for this run only (not persisted). retime_words=true re-times stored transcripts with the forced aligner from their ASR cache for this run only (no Whisper; hand-edited transcripts are skipped); check transcript_timing.json → forced_alignment.retime for skipped and failed tracks; not with force_transcribe. It fails before changing any transcript when the word aligner is not downloaded (the error names podcast bootstrap --component word-aligner). Forced alignment is otherwise on by default whenever that model is installed (transcribe.forced_alignment.enabled unset); forced_alignment.reason in transcript_timing.json says what a run resolved to. Replacing edited transcripts is refused when unattended; run attended, or the user confirms with Studio Re-transcribe. Returns Completed through <step>; when this run exported, the next lines are the export QC verdict (same as CLI pipeline run).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "pipeline_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
configNo
from_stepNo
only_stepNo
skip_stepsNo
unattendedNo
project_pathNo
retime_wordsNo
use_working_setNo
force_transcribeNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.1.1
    • addedInput schema / properties / config
      Added value: +{
      +  "anyOf": [
      +    {
      +      "additionalProperties": true,
      +      "type": "object"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Config"
      +}
    • removedInput schema / properties / config_json
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Config Json"
      -}
    • addedInput schema / properties / force_transcribe
      Added value: +{
      +  "default": false,
      +  "title": "Force Transcribe",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / project_path / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / project_path / default
      Added value: +null
    • removedInput schema / properties / project_path / type
      Removed value: -"string"
    • addedInput schema / properties / retime_words
      Added value: +{
      +  "default": false,
      +  "title": "Retime Words",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / skip_steps
      Added value: +{
      +  "anyOf": [
      +    {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Skip Steps"
      +}
    • removedInput schema / properties / skip_steps_json
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Skip Steps Json"
      -}
    • removedInput schema / required
      Removed value: -[
      -  "project_path"
      -]
  2. First observedv0.1.0

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations, the description carries the whole load and does so well: it discloses working-set read/write coupling with the GUI session, that transcripts are reused unless forced, that force_transcribe and retime_words are run-scoped and not persisted, that hand-edited transcripts are skipped, that the call fails before mutating anything when the word aligner is missing, and where to look for retime/failure evidence. What it omits is the overall side-effect profile — whether a run overwrites prior outputs, how long it blocks, and what permissions or project state are prerequisites.

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

Conciseness2/5

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

The opening sentence states purpose cleanly, but the body becomes a dense wall of parenthetical, backtick-laden fragments mixing flag semantics, working-set behavior, and JSON field paths. Detail like "check transcript_timing.json → forced_alignment.retime for skipped and failed tracks" and the forced_alignment.reason explanation is operational troubleshooting that crowds out the parameter semantics it should be front-loading.

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 9-parameter, zero-annotation mutation tool this covers the dangerous flags well and an output schema exists so return values need no explanation. But three parameters (from_step, only_step, project_path) are undocumented in both description and schema, and there is no statement of overall side effects or idempotency, leaving the definition incomplete for a pipeline-mutating operation.

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 0% across 9 parameters, so the description is the only documentation source, and it explains skip_steps, config, use_working_set, unattended, force_transcribe, and retime_words in meaningful detail including defaults and scope. It leaves from_step, only_step, and project_path entirely undefined, which is a significant hole given the zero schema coverage — an agent cannot infer step-range semantics or what project_path resolves to.

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?

"Run the production pipeline" is a specific verb plus resource, and the description shows what the run consumes (skip_steps, config override of yaml) and what it touches (working set, transcripts, alignment). It never distinguishes this from siblings like pipeline_analyze_tool or pipeline_get_config_tool, so the agent must rely on the name alone to know when to pick this one.

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?

It gives real usage constraints — retime_words is "not with force_transcribe", and replacing edited transcripts requires an attended run or explicit user confirmation — which is better than nothing. However, it never states when to use this tool instead of the analyze/get-config/set-config siblings, or when a full pipeline run is overkill.

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