Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- bidclub_list_shows — List every show in the BidClub library with its id, display name, source language, hosts, and source links. Start here when you need a show id for the show parameter of the other tools.write
- bidclub_list_episodes — List episodes newest first, optionally narrowed to one show. Returns metadata only — titles, deks, dates, durations, participant chips and source links — never the digest or transcript. Use bidclub_get_episode for content.write
- bidclub_search_episodes — Full-text search across titles, deks, TL;DRs, digests and transcripts, with a substring sweep that handles Chinese queries the tokenizer cannot segment. Returns up to 20 metadata rows, never content. When the response carries partial: true the query only covered the newest searched_recent episodes, so say so rather than reporting an absence.write
- bidclub_get_episode — Read one section of an episode. Long sections page deterministically: when the result says truncated: true, call again with offset set to next_offset and concatenate content_md until next_offset is null. Prefer tldr or digest — a transcript can exceed 100,000 characters and is rarely worth paging in full. lang selects the OUTPUT edition, not a catalogue filter; transcripts exist only in the episode's source language, so requesting a different lang for section=transcript always returns the sourcewrite
- bidclub_feed_index — The slim catalogue of every episode — one row each, metadata only. Narrow it with show or person; passing both is an error. Large responses are truncated to the newest rows with a note, so filter rather than paging.write
- bidclub_download_links — Build the download URLs for an episode or a whole show without fetching anything. Hand these to the user, or fetch one yourself when you need a complete transcript in a single request instead of paging it through bidclub_get_episode. Exactly one of slug or show is required.write
