# compositions_assemble_score

Canonical HTML page: https://bitterclip.com/docs/assistants/tools/compositions_assemble_score

Surface: app-only

Product release: 1dce717408a55fac1047e7d779177fa3ef8ede51
Public contract commit: 1ce47f7857ae3d9b6933fe83d5c33de3ae5efc64
Public contract SHA-256: 241d47d25e4b4c1dae9d2263793874d06fc4ba7bc3c78d4cf2bc63fbb32ed7dc
Descriptor SHA-256: 885d46f3ca3939dec2ace0cd6e93611c8b3f741f2d8f7a82e0adfe1452cc9a9e
Captured: 2026-09-24T16:39:30.100Z
Source: https://app.bitterclip.com/api/v1/mcp_descriptors.json

UI helper for the composition editor: assemble an ordered set of (recording, start, end) segments into ONE continuous transcript score — the words from every recording stitched in order onto a single composition timeline, with a merged speaker legend and the recording-boundary seams between chunks. Read-only and stateless (nothing is persisted, no render). The editor calls this on every edit to re-render the spliced transcript; rendering an MP4 is episode.render.

The JSON blocks below are the exact MCP descriptor projections served by Rails for the named profiles at capture time. Security schemes and resource URIs may vary by connected host.

## App descriptor

```json
{
  "name": "compositions_assemble_score",
  "title": "Assemble the composition transcript score",
  "description": "UI helper for the composition editor: assemble an ordered set of (recording, start, end) segments into ONE continuous transcript score — the words from every recording stitched in order onto a single composition timeline, with a merged speaker legend and the recording-boundary seams between chunks. Read-only and stateless (nothing is persisted, no render). The editor calls this on every edit to re-render the spliced transcript; rendering an MP4 is episode.render.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "segments": {
        "type": "array",
        "description": "Ordered segments, same shape as episode.create. Output stitches them in this order.",
        "items": {
          "type": "object",
          "properties": {
            "recording_id": {
              "type": "string",
              "description": "Recording public ID the segment is taken from."
            },
            "occurrence_id": {
              "type": "string",
              "description": "Stable Program occurrence identity when previewing an existing authored use."
            },
            "start_seconds": {
              "type": "number"
            },
            "end_seconds": {
              "type": "number"
            }
          },
          "required": [
            "recording_id",
            "start_seconds",
            "end_seconds"
          ]
        }
      },
      "selection": {
        "type": "object",
        "description": "Optional { start_seconds, end_seconds } range (composition time) to open pre-selected/highlighted on the assembled transcript.",
        "properties": {
          "start_seconds": {
            "type": "number"
          },
          "end_seconds": {
            "type": "number"
          }
        }
      },
      "row_seconds": {
        "type": "number",
        "description": "Optional transcript score row duration, in seconds. The web workspace sets this from rendered score width so narrow panes get shorter rows and dense speech remains legible."
      },
      "include_rows": {
        "type": "boolean",
        "description": "Whether to include timeline score rows. Defaults to true."
      },
      "include_reading_rows": {
        "type": "boolean",
        "description": "Whether to include reading-view prose rows. Defaults to true; the web workspace may request them lazily after first paint."
      },
      "row_format": {
        "type": "string",
        "enum": [
          "default",
          "compact_v1"
        ],
        "description": "Optional timeline-row wire format. Defaults to object rows; compact_v1 returns positional row arrays for browser/widget transfer and must be expanded by the caller."
      }
    },
    "required": [
      "segments"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ],
    "ui": {
      "visibility": [
        "app"
      ]
    },
    "openai/widgetAccessible": true,
    "openai/visibility": "private"
  },
  "outputSchema": {
    "type": "object",
    "properties": {
      "rows": {
        "type": "array",
        "description": "Assembled transcript-score rows in composition time."
      },
      "row_format": {
        "type": "string",
        "description": "Present when rows use a non-default wire format such as compact_v1."
      },
      "reading_rows": {
        "type": "array",
        "description": "Assembled reading-view prose lines (beer-goggles toggle)."
      },
      "reading_rows_deferred": {
        "type": "boolean",
        "description": "True when reading rows were intentionally omitted and may be fetched later."
      },
      "legend": {
        "type": "array",
        "description": "Merged speaker legend across the sources in range."
      },
      "seams": {
        "type": "array",
        "description": "Recording boundaries (composition_seconds + provenance labels)."
      },
      "cuts": {
        "type": "array",
        "description": "Display-only omitted same-recording transcript spans for expandable cut review, including timeline rows, reading-view rows, and a collapsed_by_default hint for long omissions. Rendering and playback still use the kept segments."
      },
      "speaker_stats": {
        "type": "array",
        "description": "Per-speaker share of the assembled composition (label, class_name, word_count, share)."
      },
      "total_seconds": {
        "type": "number"
      },
      "segment_count": {
        "type": "integer"
      }
    },
    "required": [],
    "additionalProperties": false
  }
}
```

## Errors

```json
[
  "recording_not_found",
  "invalid_time_range",
  "invalid_input"
]
```

## Examples

```json
[]
```