get_document_outline
Retrieve a compact structural map of a DOCX file's headings to quickly identify sections and scope targeted edits without scanning the entire document.
Instructions
Get a compact structural map of a document's headings (DOCX only). Returns one entry per heading paragraph with its text, outline level, source, and stable _bk_* paragraph_id — so an agent can read the cheap outline first, then scope a targeted read_file/replace_text to the right section instead of scanning the whole body. Style-based (Word HeadingN) headings only by default; set include_heuristic_headings=true to also include heuristic titles/run-in headers. Read-only.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | Output format: 'json' (default, structured outline array) or 'markdown' (indented ATX outline under `content`). | |
| file_path | No | Path to the DOCX file. | |
| include_heuristic_headings | No | When true, also include heuristically-detected headings (manual title / run-in / centered-caps) alongside Word HeadingN styles. Default: false (style-based only). |