What it does
The fix for what check_score_freshness reports: hands every stale photo the pipeline owns back to the analyser and runs a full analysis pass on them, so their scores and cull reasons reflect the current scoring rules. reselect_photos cannot do this: it re-ranks stored numbers. The user's manual keep/trash decisions are never re-scored and come back as manual_skipped. Takes as long as analyze_photos does for that many photos, so tell the user before starting on a large library. Returns analysis stats plus per-status library counts. Remote: dispatched as a background job past the call budget, like scan_directory, poll get_job_status with the returned job_id.
Parameters
reanalyze_stale_photos takes no parameters. Ask for it in plain language and the agent calls it directly.
Asking for it
You do not call this by name. You say what you want, and the agent picks the tool:
Point imagic at my shoot and tell me what you find.
The rest of the culling tools
Where it runs
On your machine. imagic's MCP server is a local process that your AI client starts; the photos never leave your disk and nothing is uploaded. That is true of every tool in the reference, including this one.
To call it you need an MCP client connected to imagic. Setup takes about three minutes for Claude Code, Cursor, VS Code, Codex, Gemini CLI and ten others.
Give your AI the whole pipeline
reanalyze_stale_photos is one of 30 tools in imagic Max. The free 500-export trial includes all of them.