create_commentary

Attach narrative analysis to a model run, or to one named output of the run. Use this after compare_runs / get_run_output to save the agent’s interpretation alongside the data it explains. If output_name is omitted, the commentary is run-level. If output_name is provided and the run has output data available, the name is validated against the same resolver as get_run_output.

Parameters

Name	Type	Required	Default	Description
run_id	Annotated[str, Field(description='UUID of the model run to attach commentary to.')]	Yes	—
text	Annotated[str, Field(description='Commentary text content.')]	Yes	—
output_name	Annotated[str, Field(description='Named output within the run that this commentary describes.')]	No	''
change_note	Annotated[str, Field(description='Optional brief note describing what changed in this version of the commentary.')]	No	''

Returns

Returns a structured object. Top-level fields:

• commentary (object)

See the response example below for the full payload shape.

Example

Tool Call

{
  "name": "create_commentary",
  "arguments": {
    "run_id": "eeeeeeee-eeee-eeee-eeee-eeeeeeeeeeee",
    "output_name": "revenue",
    "text": "Revenue beat plan by 12% in March, mostly from SaaS expansion.",
    "change_note": "Initial variance readout"
  }
}

Response

{
  "commentary": {
    "commentary_id": "ffffffff-ffff-ffff-ffff-ffffffffffff",
    "tenant_id": "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
    "project_name": "forecasts",
    "run_id": "eeeeeeee-eeee-eeee-eeee-eeeeeeeeeeee",
    "output_name": "revenue",
    "author_id": "22222222-2222-2222-2222-222222222222",
    "text": "Revenue beat plan by 12% in March, mostly from SaaS expansion.",
    "version": 1,
    "archived_at": null,
    "archived_by": null,
    "created_at": "2026-04-28T10:00:00+00:00",
    "updated_at": "2026-04-28T10:00:00+00:00"
  }
}

Notes

• Module: Run Commentary
• Requires authentication via API token or Auth0 JWT.