agent-video-engine

Overview Schema Source Related Servers Discussions Admin

media_index

Map a source video into timestamped thumbnails and transcript-linked possible retakes, returning a durable job ID for indexing without altering edits or footage.

Instructions

Map one original recording, including multiple attempts recorded in the same file. Creates timestamped thumbnails/contact sheets for video, links existing source transcript words, and groups repeated passages as POSSIBLE retakes. Never chooses the best take, splits the source, changes the edit or deletes footage. Returns a durable job ID; read job_get for the index ID. Does not transcribe automatically: use transcribe or transcript_import first for spoken take grouping. Missing transcripts allow video picture maps without spoken grouping. Reuses a cached map when source, transcript and options match.

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": {
      "projectDir": "<projectDir>",
      "expectedRevision": "<expectedRevision>",
      "assetId": "<assetId>"
    },
    "name": "media_index"
  }
}

Input Schema

Name	Required	Description
`assetId`	Yes
`projectDir`	Yes	Absolute path of the local video project directory
`maxThumbnails`	No
`intervalSeconds`	No
`expectedRevision`	Yes	Revision returned by project_inspect. Prevents overwriting newer edits.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.0.0Nov 6, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations show readOnlyHint=false, destructiveHint=false, and openWorldHint=false, and the description confirms the non-destructive behavior beyond the flag by saying it never chooses the best take, splits the source, changes the edit, or deletes footage. It adds real behavioral context: the call is asynchronous and returns a durable job ID, results may be cached, and retake detection is heuristic (POSSIBLE retakes). It does not mention the cost of producing thumbnails or whether it is safe to call again while a job is running.

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

Conciseness4/5

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

The purpose is well placed in the first sentence, and the following sentences each add a distinct piece of information (guarantees, async contract, transcript prerequisite, and caching). It is long and dense, with some sentences packed with multiple clauses, but little of it is wasted wording.

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

Completeness3/5

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

With no output schema, the description correctly says the result is a job ID that must be read through job_get, and it covers the transcript prerequisite and caching. However, for a 5-parameter indexing tool, it leaves three parameters and the thumbnail/interval tuning semantics unexplained. An agent would have to guess at the intended thumbnail sampling rate.

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

Parameters2/5

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

Schema description coverage is only 40%, only projectDir and expectedRevision have descriptions, and assetId, maxThumbnails, and intervalSeconds are left undocumented. The description does not fill that gap: it never explains what assetId identifies, what maxThumbnails caps, or what intervalSeconds controls. Thumbnail density is a central option for this tool, so this gap is material.

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

Purpose5/5

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

It uses a specific verb and resource, saying it maps one original recording and produces timestamped thumbnails and contact sheets. It distinguishes itself from transcribe and transcript_import, since it only links existing transcript words, and it names job_get for the returned job ID. An agent can tell this apart from media_index_get and the family of media tools without opening a schema.

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

Usage Guidelines5/5

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

It gives explicit prerequisites: transcripts must exist first via transcribe or transcript_import, and without them the tool degrades to a video picture map with no spoken grouping. It states when caching is reused, when source, transcript, and options match, and where to read the resulting index ID via job_get. The boundary against sibling tools is explicit rather than implied.

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