Search FRED for economic data series matching a text query.

Use this first to turn a natural-language request (e.g. "real median household income, seasonally adjusted") into a concrete series_id for get_observations. Results are ordered by popularity.

Args: query: Free-text search, e.g. "unemployment rate" or "10-year treasury". limit: Max number of series to return (1-50).

Get metadata for a specific FRED series (title, units, frequency, range, notes).

Args: series_id: The FRED series ID, e.g. "UNRATE" or "GDPC1".

Get the observations (actual time-series values) for a FRED series.

Returns a compact list of {date, value} points plus metadata. To stay within the client's result-size limit, the point count is capped; if a series has more points than the cap over your window, narrow the date range or aggregate via frequency. A value of "." means the observation is missing for that date.

Args: series_id: The FRED series ID, e.g. "UNRATE". start_date: Inclusive start "YYYY-MM-DD". Omit for the series start. end_date: Inclusive end "YYYY-MM-DD". Omit for the latest. units: Optional transform: "lin" (levels), "chg", "ch1", "pch", "pc1" (year-over-year %), "pca", "cch", "cca", "log". frequency: Optional down-aggregation: "d","w","bw","m","q","sa","a". Omit to use the series' native frequency. sort_order: "asc" (oldest first) or "desc" (newest first). limit: Max points to return (capped at the server maximum).