Read an article with smry
get_articleFetch clean, source-grounded text for a public article or YouTube URL, budgeted to a token limit and addressable by paragraph anchor. Returns an outline of headings (empty when the source has none), the requested window, and a next_cursor when more remains. Prefer search_article when you have a specific question rather than needing the whole text.
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": {
"url": "<url>"
},
"name": "get_article"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| cursor | No | ||
| max_tokens | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| title | Yes | ||
| author | Yes | ||
| outline | Yes | ||
| language | Yes | ||
| cache_hit | Yes | ||
| publisher | Yes | ||
| to_anchor | Yes | ||
| reader_url | Yes | ||
| source_url | Yes | ||
| from_anchor | Yes | ||
| next_cursor | Yes | ||
| published_at | Yes | ||
| responded_at | Yes | ||
| total_blocks | Yes | ||
| total_tokens | Yes | ||
| content_quality | Yes | ||
| tokens_returned | Yes | ||
| extraction_source | Yes |