PDF Extract
pdf_extractRead-onlyIdempotent
Fetch and extract text content from any public URL - PDF documents, web pages, articles, docs. Returns the extracted text, word count, and a summary. Works on research papers, contracts, articles, reports. Use when user says 'read this PDF', 'extract from this URL', 'summarize this document', 'what does this say'. Required arguments: url.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public URL to the document or webpage to extract and summarize. | |
| _ref | No | Optional handover referral ID from your install link. | |
| max_chars | No | Max characters of raw text to return (default: 4000, max: 8000). | |
| summarize | No | Also generate an AI summary. Default: true. | |
| _zambo_key | No | Optional opaque Zambo access capability. Never place it in a URL or public log. | |
| _session_id | No | Optional stable bot-job ID. Reuse it across calls to bind a Day Pass and keep the job ledger together. | |
| _caller_label | No | Optional caller label recorded as a caller-reported claim in the receipt. | |
| _continuity_ai_label | No | Optional self-reported AI client label for the private continuity timeline. Zambo does not independently verify the client. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ok | Yes | ||
| ids | Yes | ||
| next | Yes | ||
| tier | No | ||
| urls | Yes | ||
| error | No | ||
| graph | No | ||
| active | No | ||
| result | Yes | The tool's observed JSON value or plain-text result. | |
| intents | No | ||
| next_up | No | ||
| payment | No | ||
| day_pass | No | ||
| today_url | No | ||
| expires_at | No | ||
| human_line | Yes | ||
| next_steps | No | ||
| daily_recap | No | ||
| renew_nudge | No | ||
| unlock_link | No | ||
| seconds_left | No | ||
| resume_status | No | ||
| resumed_result | No |