video_read
Fetch bounded batches of saved video images with timestamps for visual inspection, and acknowledge each batch before requesting another to prevent image accumulation.
Instructions
Read 1..12 saved images (default12, max8MiB encoded image bytes). Returns currently available images without waiting to fill a batch and timestamps. after is zero-based, -1 initially. Partial pages may be limited by bytes; follow nextAfter. The host chooses evidence scope, not necessarily every image. Inspect the batch in a separate model step; call video_review ack before another image fetch. Pending batches block subsequent fetches so a loop cannot accumulate hundreds of images. replay retries lost responses. hasMore/exhausted describe production/cursor only; visualDelivery is legacy sent-byte bookkeeping, visualReview records caller acknowledgements and the chosen plan. Images default to format=jpeg (FFmpeg q:v4, 4:4:4); request format=png for original PNG detail. Encoding is cancellable with 2 active conversions per MCP process, at most 24 queued, a 30s queue deadline and a 10s execution deadline. Every image response is limited to 8MiB encoded bytes. Saved storyboard PNGs are retained. Acknowledge the pending batch before switching formats; replay preserves its original format and bytes.
The HOST chooses evidence depth from the user request and actual subtitle/ASR quality and coverage: text alone, selected storyboards, all storyboards, or targeted higher-quality follow-up. Subtitles, ASR and images are independently optional; choose any combination. For text-only media use audio_start/audio_url_start (audio-bearing video files/pages are accepted) without a visual job. No mandatory image retrieval, all-images rule, fixed answer format or mandatory ASR. Use video_review action=plan to record visual=none|selected|all; revise as evidence changes. Missing subtitles do NOT block usable images, and a video-only stream does not prove missing source audio. Each image response has a pending batch. Return images AND timestamp metadata to the model, inspect the chosen images, then call video_review action=ack with batchId and explicit viewedIndices (empty [] releases uninspected images without credit). ONLY THEN fetch another batch. Never accumulate many video_read calls inside one code/exec result: return control to the model after each bounded batch. Transport errors leave the batch pending: video_review replay retries it; status/reviewId support resume. Acknowledgement is a caller assertion, not proof of comprehension. Keep any semantic working notes in the Agent workspace, not in MCP evidence. Before finishing, video_review finish checks only the HOST-CHOSEN visual scope and pending image receipts, not text reading completion. The host must still judge if that scope answers the user, and state relevant gaps. Honest incomplete-work disclaimers do not justify abandoning feasible work. session_stop cleanup cancels processing but does not complete reading; user_cancelled is only for an explicit user cancellation. Audio-only workflows remain independent.
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": {
"id": "<id>"
},
"name": "video_read"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| after | No | ||
| limit | No | ||
| format | No | ||
| waitSeconds | No |