读文档结构化块
feishu_doc_blocksRead a Feishu document as structured blocks with block IDs, types, and extracted text, so you can locate specific paragraphs or tables and run precise block-level operations.
Instructions
按块(block)读一篇云文档的结构:每块有 block_id、block_type 与内容。和 feishu_doc_read 的区别:doc_read 给的是拼接好的纯文本,适合通读;doc_blocks 保留段落/标题/表格/图片块的分块结构,适合定位「第几段」「哪个表格」以及后续按 block_id 做精细操作。飞书文档的块类型是数字编码(如 2=文本、3-11=各级标题、31=表格),本工具会把能识别的文字内容抽出来,识别不了的块只给类型码。
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"document_id": "<document_id>"
},
"name": "feishu_doc_blocks"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| max_pages | No | 最多翻几页,默认 3(防止超大文档一次拉爆) | |
| page_size | No | 每页块数,默认 200,最大 500 | |
| document_id | Yes | 文档 id(docx 链接里 /docx/ 后面那串,不是整个 URL) |