semantic_search
Find emails and attachments by meaning using natural-language queries, with snippets showing the best-matching passage and whether meaning, keywords, or both matched.
Instructions
Find emails and attachments by meaning. Each result is one email with the best matching passage as
its snippet, match says whether that passage is the subject, the body or an attachment, and
matched says whether meaning, keywords or both found it.
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": {
"query": "<query>"
},
"name": "semantic_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | hybrid: meaning plus keywords, fused (default). semantic: meaning only | hybrid |
| limit | No | ||
| query | Yes | What you remember, in your own words, in any of about 100 languages. No exact keywords needed | |
| folder | No | Folder name contains this text | |
| sender | No | From: sender name or address contains this text | |
| account | No | Account name contains this text | |
| date_to | No | Latest date, inclusive, YYYY-MM-DD or ISO 8601 (UTC) | |
| date_from | No | Earliest date, YYYY-MM-DD or ISO 8601 (UTC) | |
| recipient | No | To/Cc/Bcc contains this text | |
| has_attachment | No |