Start an image search session
image_search_startSearch reference images from multiple providers using a natural-language query, then filter and return selected candidates as a numbered grid with metadata.
Instructions
Parse a natural-language query into keywords (unless keywords are given), search all configured image providers in parallel, dedupe, render a numbered composite grid (round 'a', cell ids a1..aN), and run a multimodal filter that returns the selected cell ids. Returns the grid file path, the selected ids, the metadata table, and the keywords actually used.
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": "image_search_start"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Max candidates in this round (default: grid capacity) | |
| query | Yes | Natural-language image request, e.g. 'space nebula illustrations for a podcast cover' | |
| filter | No | false = skip the server-side vision filter and return all candidates (use when the calling model is multimodal and will look at the grid itself); default follows FILTER_MODE | |
| criteria | No | Style / quality criteria for filtering, e.g. 'flat vector, no text, dark background' | |
| keywords | No | Explicit search keywords; skips LLM parsing when given | |
| safe_search | No |