Find the passages of an article that answer a question
search_articleRead a public article or YouTube URL and return only the passages relevant to your query, each anchored to its paragraph and labelled with the section it sits under. Use this instead of get_article whenever you have a specific question about a link — it answers in a fraction of the tokens and the anchors stay citable.
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>",
"query": "<query>"
},
"name": "search_article"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| query | Yes | ||
| cursor | No | ||
| max_tokens | No | ||
| max_passages | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| title | Yes | ||
| author | Yes | ||
| language | Yes | ||
| passages | Yes | ||
| cache_hit | Yes | ||
| publisher | Yes | ||
| reader_url | Yes | ||
| source_url | Yes | ||
| next_cursor | Yes | ||
| published_at | Yes | ||
| responded_at | Yes | ||
| total_blocks | Yes | ||
| total_tokens | Yes | ||
| matched_blocks | Yes | ||
| content_quality | Yes | ||
| tokens_returned | Yes | ||
| extraction_source | Yes |