name: query_user_feedback
description: "Search and aggregate user feedback, support tickets, and NPS responses related to a topic or feature"
when_to_use: "When gathering qualitative evidence for prioritization, understanding pain points, or validating a problem hypothesis"
parameters:
  query:
    type: string
    description: "Search term or topic to match against feedback content"
    required: true
  sources:
    type: array
    description: "Feedback sources to include, e.g. [\"intercom\", \"zendesk\", \"app_reviews\", \"nps\"]"
    required: false
  from:
    type: string
    description: "Start date for the feedback window in ISO 8601 format"
    required: false
  sentiment:
    type: string
    description: "Filter by sentiment classification"
    enum: [positive, negative, neutral]
    required: false
returns:
  type: object
  description: "Aggregated feedback with theme clusters, sample quotes, and sentiment breakdown"
  properties:
    query:
      type: string
    total_matches:
      type: integer
    themes:
      type: array
      items:
        type: object
        properties:
          theme:
            type: string
          count:
            type: integer
          sample_quotes:
            type: array
            items:
              type: string
    sentiment_breakdown:
      type: object
      properties:
        positive:
          type: integer
        neutral:
          type: integer
        negative:
          type: integer