Description: Adds supported Apple Music content to the authenticated user's favorites. Supported types: artists. Constraints: Requires an authenticated user session. Do NOT call from free-form chat. This tool is only for widget actions (e.g., user clicks Add/+ on a result in the Apple Music widget). Do not trigger on behalf of third parties or external systems. Only invoke for items that were returned by the Apple Music Widget tool; do not act on arbitrary or unseen items.

Description: Adds supported Apple Music content to the authenticated user's library. Supported types: songs, albums, playlists. Constraints: Requires an authenticated user session. Do NOT call from free-form chat. This tool is only for widget actions (e.g., user clicks Add/+ on a result in the Apple Music widget). Do not trigger on behalf of third parties or external systems. Only invoke for items that were returned by the Apple Music Widget tool; do not act on arbitrary or unseen items.

Description: Creates a new user playlist from a list of song IDs. Output: A playlist resource object or a confirmation object with the new playlist's URL. Constraints: Do NOT call from free-form chat. MUST be called as a subsequent step after song/music-video IDs have been fetched from the matching tool. The title and description can be inferred by the model from the user's original request, and modifiable by the user. Requires an authenticated user session.

Description: Batch-retrieves full song resource objects for a provided list of song titles and (optionally) artists. This is a data-hydration tool, not a discovery or search tool. Use this tool after generating a playlist or list of tracks from model reasoning or user input. The model should first compile up to 25 candidate track titles (with optional artists) based on its music knowledge, cultural reasoning, and any relevant user context, and then invoke this tool to retrieve verified Apple Music metadata and links. Usage Guidance: This tool should be triggered in two user journeys: 1. After the Search tool is used: - Parse the Search tool results and extract the songs or music videos returned. 2. When the user requests a playlist or list of songs/music videos: - Interpret the user's intent (e.g., genre, mood, vibe, audio attributes). - Use internal music knowledge to generate up to 25 tracks that match the intent. - Pass those tracks to this tool for enrichment (e.g., album art, preview URLs). 3. When presenting the results of a playlist request, the model must clearly state in the user's language: "Here's a draft of your playlist. To create it in Apple Music, click the Open Playlist in Apple Music button." The model must not imply that a playlist has been created automatically. Also, do not ask the user to add more songs to the playlist as a follow-up question. Constraints: Use this tool only to enrich a list of songs already generated by the model from a user query (e.g., '90s dance songs', 'sad songs for a rainy day'). It must not be used for discovery or search. Critical Rules: - Do not fabricate, truncate, or alter entity names, metadata, or links. - Do not generate lyrics, biographies, or external content. - Only surface Apple Music deep links returned directly by the API; never construct your own. - Never display a deep_link as a raw URL. Show it only through widgets or Apple Music navigation.

Do not invoke in freeform chat.