{"version":"2.1.242","anchor":"read-tool-returns-pdf-pages-as-structured-entries-with-per-p","canonical_anchor":"read-tool-returns-pdf-pages-as-structured-entries-with-per-p","heading":"Read tool returns PDF pages as structured entries with per-page errors","tier":"notice","area":"Read Tool","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.242\/e\/read-tool-returns-pdf-pages-as-structured-entries-with-per-p","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.242","markdown":"### Read tool returns PDF pages as structured entries with per-page errors\n\nOne unreadable PDF page no longer costs you the rest of the document.\n\n**What**\n\nReading a PDF now returns a first page plus a list of page images, each with its own base64 data, media type and error field, so one unreadable page no longer costs you the rest of the document.\n\n**Details**\n\n- A page that failed carries an `error` string explaining why and empty base64; the error is set only when base64 is empty.\n- The image bytes are transient and are not persisted on the recorded tool result.\n- Counters for `imagesOmitted`, `imagePagesFailed`, `imagePagesFailedOmitted` and `documentsOmitted` are surfaced as notes.\n\n**Evidence**\n\n`Why the page could not be processed as an image; set only when base64 is empty`\n\n- Area: Read Tool\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}