Search Flickr photos
flickr_photos_searchSearch Flickr photos by text, tags, dates, licence, media, user or place to find matching images. Filter by geo, upload or taken windows and license type, with cursor pagination.
Instructions
Search Flickr photos by text, tags, dates, licence, media, user or place. Optional inputs: cursor, page, limit, query, tags and 13 more. Returns a list (use cursor when paginated).
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": {
"context": "<context>",
"llm_model": "<llm_model>"
},
"name": "flickr_photos_search"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number, 1-based. Default: 1. A page past the last returns an empty list with `hasMore: false`. Prefer `cursor` when continuing. | |
| sort | No | Order. Default: relevance. For a taken window use `date-taken-asc` or `date-taken-desc`: pages end as soon as the window is passed. Newest-first sorts can repeat a row; `uploadedFrom`/`uploadedTo` give a stable walk. | |
| tags | No | Space- or comma-separated tags. | |
| limit | No | Rows per page, 1 to 100. Default: 100. | |
| media | No | Restrict results to `photos` or `videos`. | |
| query | No | Free text to match photo titles, descriptions or tags. | |
| cursor | No | Cursor from `page.nextCursor` of the previous response. It only works with the same filters. Send it without `page`; it keeps the page size it was issued with, so `limit` may be sent again and has no effect. | |
| hasGeo | No | Only geotagged photos. | |
| radius | No | Radius in kilometres for a geo search. | |
| userId | No | Only this user photos. | |
| context | Yes | Describe the user's underlying goal in one sentence, not the tool you are calling. | |
| license | No | Licence ids, comma-separated. `0` all rights reserved; `1` to `6` and `11` to `16` Creative Commons; `7` no known copyright; `8` US government work; `9` and `10` public domain. | |
| tagMode | No | Whether every tag or any tag must match. Default: all. | |
| takenTo | No | Latest taken time as in `dates.takenAt`, ISO 8601 or a date (00:00; use `2024-01-31T23:59:59` for a whole day). A time zone or offset is ignored. Pages can hold fewer rows than `limit`. | |
| latitude | No | Latitude for a geo search. | |
| llm_model | Yes | The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess. | |
| longitude | No | Longitude for a geo search. | |
| takenFrom | No | Earliest taken time as in `dates.takenAt`, ISO 8601 or a date (00:00). A time zone or offset is ignored. Before `takenTo`. Pages can hold fewer rows than `limit`; sort by taken date to end paging at the window. | |
| uploadedTo | No | Latest upload time, ISO 8601 or a date. A date-only value means 00:00 UTC on that day; to include the whole day, pass a full time such as `2024-01-31T23:59:59Z`. | |
| uploadedFrom | No | Earliest upload time, ISO 8601 or a date. A date-only value means 00:00 UTC on that day. | |
| conversation_id | No | Echo the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it. |