analytics_metric_query

Tool

analytics_metric_query

Compute declared metrics from the analytics semantic layer for the current product, bucketed by time and optionally grouped by one declared dimension.

Compute declared metrics from the analytics semantic layer for the current product, bucketed by time and optionally grouped by one declared dimension. Deterministic: entity, metric and dimension names are resolved against the semantic catalog, never generated. Prefer this over analytics_query_run whenever the question is a metric over time — no LLM, no SQL generation. Where the catalog gives an entity a `propertiesColumn`, `group_by` and a filter dimension also accept `props.<key>` to read one raw event property; property values always compare as strings.

Behavior

HTTP: POST /analytics/metrics/query

Arguments

Name	Type	Required	Description
to	string	•	Inclusive last day (UTC)
from	string	•	Inclusive first day (UTC)
grain	string	•	Time bucket size
entity	string	•	Semantic view name from the catalog
filters	array	—	Equality filters on declared dimensions, or on `props.<key>` event properties
metrics	array	•	Declared metric names to compute
group_by	string	—	One declared dimension, or `props.<key>`, to group by

Response

Field	Type	Always	Description
meta	object	•
series	array	•

Try it

Compute declared metrics from the analytics semantic layer for the current product, bucketed by time and optionally grouped by one declared dimension.

When to use

Example

Ask your agent something like this:

Compute declared metrics from the analytics semantic layer for the current product, bucketed by time and optionally grouped by one declared dimension.

The agent will invoke analytics_metric_query with these arguments:

{
  "to": "<to>",
  "from": "<from>",
  "grain": "<grain>",
  "entity": "<entity>",
  "metrics": "<metrics>"
}