Aggregate and product drilldown

Query an aggregate scope, then rank products under exactly the same filters.

Document ID: agent.dataset.tmall.task.aggregate_drilldown

Authenticated runtime tools and each query response are authoritative for tenant scope and current data coverage.

This is an MCP query composition, not a complete business report; see Research Methods in the Agent Docs for complete workflows.

Required inputs

scopeRequired · search_values

Exact category value

category_l3

timeRequired · user_required

Analysis time range

ranking_metricOptional · user_required

Metric used to rank products

Default: gmv · Allowed values: gmv, units

top_nOptional · user_required

Number of products to return

Default: 20

Execution steps

1
resolve_scope · search_values
Resolve the spoken category value.
Request contract
category_l3 ← $scope
2
query_scope · query_metrics
Query aggregate GMV and units.
Request contract
metrics: gmv, unitsfilter: category_l3 eq $scopetime: $time
3
query_products · query_metrics
Query products using the same scope and time.
Request contract
metrics: gmv, unitsgroup_by: product_id, title, product_urlfilter: category_l3 eq $scopetime: $timeorder_by: $ranking_metric desclimit: $top_n

Call example

Replace example values with exact user inputs or platform values returned by search_values.

search_values

{
  "dataset": "tmall",
  "field": "category_l3",
  "kw": "示例品类",
  "limit": 10,
  "task_query": "使用 tmall 数据执行汇总与商品下钻；scope=示例品类，time={\"last_complete_months\":3}，ranking_metric=gmv，top_n=10"
}

query_metrics

{
  "additional_queries": [
    {
      "filters": [
        {
          "field": "category_l3",
          "op": "eq",
          "value": "示例品类"
        }
      ],
      "group_by": [
        "product_id",
        "title",
        "product_url"
      ],
      "limit": 10,
      "metrics": [
        "gmv",
        "units"
      ],
      "name": "query_products",
      "order_by": [
        {
          "dir": "desc",
          "field": "gmv"
        }
      ],
      "time": {
        "last_complete_months": 3
      }
    }
  ],
  "dataset": "tmall",
  "filters": [
    {
      "field": "category_l3",
      "op": "eq",
      "value": "示例品类"
    }
  ],
  "main_query_name": "query_scope",
  "metrics": [
    "gmv",
    "units"
  ],
  "task_query": "使用 tmall 数据执行汇总与商品下钻；scope=示例品类，time={\"last_complete_months\":3}，ranking_metric=gmv，top_n=10",
  "time": {
    "last_complete_months": 3
  }
}

Agent computation

rank_products · rank

Rank products by the requested metric.

source_steps: query_products

Output policy

Show the aggregate before the product ranking, with complete product identity.

Stop conditions

Stop if the scope cannot be resolved exactly.

Limitations

Keep the aggregate and drilldown filters identical.