Energy Aspects

Retrieve EA Live posts — short, real-time market updates and analyst commentary from Energy Aspects — via semantic search. Prefer this over `get_publications` when looking for recent news or intraday commentary rather than long-form research reports. Read-only. Parameters: `query` (required, str) — natural-language or keyword description of the topic; `from_` (optional, str) — earliest post date filter, accepts yyyy-MM-dd or yyyy-MM-ddTHH:mm:ssZ; `to` (optional, str) — latest post date filter, same format as from_; `limit` (optional, integer 1–50, default 10) — number of results to return. Each result in the returned JSON array contains: `title` (str), `metadata_content` (post summary), `published_at` (ISO 8601 UTC datetime, e.g. "2025-03-14T09:00:00Z"), `content_type` (str), `chunks` (array of relevant text excerpts, each with `content`, `order`, `score`), `licenses` (array of str), and `url` (canonical EA portal link). On error, surface the message and ask for corrected inputs. For questions spanning publications, EA Live posts, and timeseries together, prefer `get_insight_and_data`. IMPORTANT: Always cite sources using the `url` field formatted as a markdown link: [Title](url).

get_ea_live_posts

Retrieve publications, EA Live posts, and timeseries data in a single parallel request. This is the preferred starting tool for broad or initial research questions — use the dedicated tools (`get_publications`, `get_ea_live_posts`, `get_timeseries_data`) only when targeting a specific content type. Read-only. Parameters: `query` (required, str) — natural-language or keyword description of the topic; `from_` (optional, str) — earliest date filter applied to all content types, accepts yyyy-MM-dd or yyyy-MM-ddTHH:mm:ssZ; `to` (optional, str) — latest date filter, same format as from_; `limit` (optional, integer 1–50, default 10) — maximum results returned per content type. Returns a JSON object with keys `publications`, `ea_live`, and `timeseries` (each an array of results with the same schema as their respective dedicated tools) plus an `errors` object reporting any per-source failures — partial results from successful sources remain valid even when one source errors. IMPORTANT: Always cite sources using the `url` field formatted as a markdown link: [Title](url).

get_insight_and_data

Retrieve Energy Aspects in-depth research publications and analysis via semantic search. Read-only. Parameters: `query` (required, str) — natural-language or keyword description of the topic; `from_` (optional, str) — earliest publication date filter, accepts yyyy-MM-dd or yyyy-MM-ddTHH:mm:ssZ; `to` (optional, str) — latest publication date filter, same format as from_; `limit` (optional, integer 1–50, default 10) — number of results to return. Each result in the returned JSON array contains: `title` (str), `metadata_content` (editorial summary/abstract), `published_at` (ISO 8601 UTC datetime, e.g. "2025-03-14T09:00:00Z"), `content_type` (e.g. "report"), `chunks` (array of relevant text excerpts, each with `content`, `order`, `score`), `licenses` (array of str), and `url` (canonical EA portal link). On error, surface the message and ask for corrected inputs. For questions spanning publications, EA Live posts, and timeseries together, prefer `get_insight_and_data`. IMPORTANT: Always cite sources using the `url` field formatted as a markdown link: [Title](url).

get_publications

Retrieve Energy Aspects time-series datasets — historical values and forecasts for energy market metrics — via semantic search. Read-only. Parameters: `query` (required, str) — natural-language description of the metric (e.g. "US crude oil production", "European natural gas demand"); `from_` (optional, str) — earliest data-point date filter, accepts yyyy-MM-dd or yyyy-MM-ddTHH:mm:ssZ; `to` (optional, str) — latest data-point date filter, same format as from_; `limit` (optional, integer 1–50, default 10) — number of datasets to return; `release_date` (optional, str yyyy-MM-dd) — return data as it appeared at a specific release or revision date (point-in-time query). Each result in the returned JSON array contains: `metadata` object with `description` (dataset label), `country`, `country_iso`, `region`, `sub_region`, `aspect`, `aspect_subtype`, `category`, `category_subtype`, `unit` (e.g. "mb/d"), `frequency` (e.g. "monthly"), `lifecycle_stage` (e.g. "forecast" or "history"), `forecast_start_date`, `release_date`, and `source`; `data` object mapping date strings to numeric values (e.g. {"2025-01": 13.2}); `dataset_id` (str); and `url` (EA portal chart link). On error, surface the message and ask for corrected inputs. For questions spanning publications, EA Live posts, and timeseries together, prefer `get_insight_and_data`. IMPORTANT: Always cite sources using the `url` field formatted as a markdown link: [Title](url).

get_timeseries_data