video-sense

Overview Schema Source Related Servers Discussions Admin

session_stop

Stops an active video or audio task, cancels preparation, ASR, and visual decoding, and keeps saved evidence; use cleanup for normal stop or user_cancelled for explicit cancellation.

Instructions

reason=cleanup (default) stops producers without declaring the review complete; reason=user_cancelled releases the review only when the user explicitly cancels. Stop this server-owned audio/video task: source preparation, resolver, audio acquisition, ASR and visual decoder/network connections as applicable; retain saved evidence. Does not delete files or stop unrelated processes.

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": "session_stop"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes
`reason`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.9.0Nov 5, 2026

TDQS

A3.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnly=false, destructive=false, idempotent=false, openWorld=false; the description adds material context beyond that, notably that saved evidence is retained, files are not deleted, unrelated processes are untouched, and cleanup cancels processing without completing reading. That is exactly the kind of consequence disclosure a stop tool needs. It does not address idempotency (what happens on a second stop of the same id) or what the call returns, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The relevant stop semantics occupy roughly two sentences; the remaining bulk is unrelated host workflow guidance about evidence depth, storyboards, video_read batching, video_review ack/replay, and ASR independence, which belongs to other tools and buries the operative content. The definition is not front-loaded on the action, and the reader must wade through many sentences that do not earn their place here.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter lifecycle tool with no output schema, the description should define `id`, state what a stopped task leaves behind and what the caller gets back, and whether repeated stops are safe; none of that is present. The `reason` semantics and the non-destructive guarantee are covered, but the required identifier is completely undefined and the large off-topic section displaces the information an agent actually needs to invoke this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry both parameters. It does an excellent job on `reason`, defining the semantic difference between cleanup and user_cancelled and their effect on review state. It says nothing about the required `id` parameter (a UUID) — an agent must infer whether that is the task/session id returned by a start tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The second sentence states a specific verb and resource: "Stop this server-owned audio/video task: source preparation, resolver, audio acquisition, ASR and visual decoder/network connections as applicable; retain saved evidence." It also bounds scope negatively ("Does not delete files or stop unrelated processes"), which separates it from destructive siblings. It falls short of 5 because the opening sentence leads with `reason` semantics rather than the action, and no sibling is named directly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly distinguishes the two modes: cleanup "stops producers without declaring the review complete," while user_cancelled "releases the review only when the user explicitly cancels," and it repeats that user_cancelled is only for explicit user cancellation. That is genuine when-to-use/when-not guidance for both enum values. It does not, however, say when to call session_stop at all versus just letting a job run, nor how it relates to siblings like video_status or video_review finish.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server