List every metric the semantic layer defines.

Args:
    search: Optional case-insensitive substring to filter metric names,
        labels and descriptions. Leave empty to list all.

Returns the metric name, label, type, one-line description and the short
definition. Use `describe_metric` for the full governance block.

Return the full governed definition of one metric.

Args:
    metric: The exact metric name, as returned by `list_metrics`.

Returns the definition, the assumption it rests on, the trade-off accepted
when it was chosen, what breaks if someone defines it differently, its
grain, and the measures or metrics it is computed from. This is the
authoritative text — it is read from the compiled dbt manifest, which is
generated from models/semantic/metrics.yml.

List the dimensions a given set of metrics can legitimately be grouped by.

Args:
    metrics: One or more metric names, comma-separated. When several are
        given, only dimensions valid for *all* of them are returned —
        which is the honest answer, because MetricFlow will refuse a
        group-by that has no join path to one of the metrics.

Dimension names are returned in MetricFlow's `entity__dimension` form,
which is exactly what `query_metrics` expects in `group_by`.

Run a metric query through MetricFlow and return the rows, together with the
governed definition of every metric involved.

Args:
    metrics: Metric names, comma-separated. Must already exist in the layer.
    group_by: Dimensions to group by, comma-separated, in MetricFlow's
        `entity__dimension` form (e.g. `user__acquisition_medium`).
        Use `metric_time` for the metric's own time axis, optionally with a
        grain suffix such as `metric_time__week`.
    start_time: Inclusive ISO date lower bound on metric_time, e.g. 2021-01-01.
    end_time: Inclusive ISO date upper bound on metric_time.
    where: A MetricFlow filter expression, e.g.
        "{{ Dimension('user__first_device_category') }} = 'mobile'".
        Dimensions must be referenced through the Dimension() wrapper; raw
        column names are rejected by the layer, not by this server.
    order_by: Fields to sort by, comma-separated. Prefix with `-` for
        descending, e.g. `-metric_time`.
    limit: Maximum rows to return. Capped at 500.

The response always includes a `governance` block. Report it alongside the
numbers rather than presenting the figures bare.

Return the SQL MetricFlow would run for a query, without running it.

Args:
    metrics: Metric names, comma-separated.
    group_by: Dimensions to group by, comma-separated.
    start_time: Inclusive ISO date lower bound on metric_time.
    end_time: Inclusive ISO date upper bound on metric_time.
    where: A MetricFlow filter expression.

Useful for showing a person how a metric is actually computed, and for
checking a query's cost before spending warehouse credits on it.

Report whether the semantic layer is ready to serve queries: manifests
present, MetricFlow available, warehouse credentials configured.

Call this first if a query fails for reasons that look environmental.