Answer a data question
ask_anythingTakes a plain-language data question (official statistics, central bank rates, FX, energy, weather, holidays, research metadata). Every answer has an outcome. "answer": the value, only when the asked measure is word for word one known name of a series and its place, level and time fit and no other series fits as well; it carries answered_with (compare it with your question before you use it); a value history holds only the newest values, full true returns all of it. "candidates": otherwise, like find_data, up to 10 labelled series (publisher title, place with code and level, unit, latest value, range, source, licence) with the call_api arguments of each: choose the one whose measure, place and time match the question and pass its arguments to call_api (that second call returns the value); if none matches, tell the user this service does not have it. "none": nothing fits, with a reason. mode "candidates" always lists, mode "strict" gives the answer or none, never candidates. Examples: "population of pakistan", "unemployment rate california 2024". When to use: for any data question when you do not know the endpoint id. For a task with several figures or countries pass questions, not one call each. Use call_api instead when you already have an id, get_series for a long numeric history. Read-only, no API key or signup. Free quota: 1000 calls/day per IP, shared across tools.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "ask_anything"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| full | No | outcome answer: true returns the whole value history (default: only the newest values and those of the years asked for, see truncated). | |
| mode | No | auto (default): outcome answer when exactly one series is what is asked, otherwise candidates, otherwise none. candidates: always the candidates (or none). strict: answer or none, never candidates, for callers that cannot make a second call. | |
| query | No | Question or keywords, max 200 characters | |
| questions | No | Several questions answered in one call, in place of query. Split a task into one question per figure and place, e.g. ["inflation chile", "inflation peru"]. Each counts as one call of the quota. |