extract_tables Leave feedback

extract_tables pulls tables out of a document as Markdown (the default — it renders as a real table in chat, VS Code and GitHub) or as JSON rows for programmatic use. Example prompt: “Extract the tables from invoice.pdf.”

Tool description (as the AI agent sees it):

Extracts tables from a document and returns them as Markdown (default) or JSON. Supports PDF, DOCX, XLSX, PPTX, HTML, and other tabular formats. Markdown tables render instantly in VS Code, GitHub, and AI chat — use this format to visually review table data right in the response. Use format=‘json’ to get a structured array of rows for programmatic processing or further manipulation. Call this tool immediately whenever the user asks to extract, read, or view tables from a document. Do NOT pre-check whether files exist — just pass the filename the user provided. Returns either a Markdown document (multiple ### Table N (page N, R×C) sections) or a JSON array of { table, page, rows, columns, data: string[][] } objects. On failure, the response text starts with ‘Table extraction failed for’ followed by the underlying exception type, message, and inner-exception chain.

{
  "name": "extract_tables",
  "arguments": {
    "file": {
      "filePath": "invoice.pdf"
    },
    "format": "markdown"
  }
}

Markdown tables, or a structured array of rows when format: "json".

The choice matters more than it looks:

• markdown — you are going to look at the data. It renders immediately, which makes review fast.
• json — the agent is going to compute with the data: sum a column, compare against a record, write it somewhere.

Restrict to a page when the document is long; table detection across a hundred pages is work you do not need.

On failure the text starts with Table extraction failed for, followed by the exception type and message.

• “Extract the tables from invoice.pdf.”
• “Get the line-items table as JSON so you can total it.”
• “Show me the table on page 4.”
• “Pull the price table out of each of these PDFs.”

See it used end-to-end: Extract tables into structured data.