Skip to main content
Glama

analyze

Extracts word-level transcripts, face positions, shot boundaries, and beat times from a video asset to support captions, reframing, and beat-synced edits; returns a jobId.

Instructions

Analyse an asset. transcript = word-level speech-to-text (clip picking, captions, silence removal); faces = face positions (auto-face / split reframing); scenes = shot boundaries; beats = music tempo + beat times (beat-synced cuts). Cached; returns a jobId.

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": {
      "assetId": "<assetId>",
      "include": "<include>"
    },
    "name": "analyze"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitNo
forceNo
modelNoWhisper model override, e.g. small, medium, large-v3-turbo
promptNoNames or terms to help transcription spell things right
assetIdYes
includeYes
languageNoISO code like en, hi, pa; omit to auto-detect

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description must carry the behavioral burden, and it does disclose two important traits: results are cached and the call returns a jobId rather than finished data. It omits the cost/expense profile of analysis and, critically, leaves the `force` (cache bypass) and `wait` (blocking up to 45s) semantics unexplained, which are the behaviors an agent most needs to reason about.

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

Conciseness5/5

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

Front-loaded with the verb and resource, then a tight semicolon-delimited enumeration that gives every clause a purpose. The telegraphic "key = value (use case)" format is dense but unambiguous, with no filler sentences.

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?

For a 7-parameter tool with no annotations, no output schema, and 43% schema coverage, the description covers the include semantics and the async/cache model well but leaves the polling contract, force semantics, and any cost expectations unstated. Adequate as a starting point, not complete for confident invocation.

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 coverage is only 43%, but the description adds real value by glossing all four `include` enum values with their downstream use cases, something the bare enum list cannot convey. However, `wait` and `force` — the two behaviorally significant, undocumented parameters — are left entirely to inference.

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 description opens with a specific verb and resource ("Analyse an asset") and then enumerates exactly what each analysis kind produces, so an agent knows precisely what it gets. It stops short of distinguishing itself from result-retrieval siblings like analysis_get or transcript_get, even though "returns a jobId" implies a follow-up step.

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

Usage Guidelines3/5

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

Usage is only implied: the include options and "cached; returns a jobId" hint that this is the entry point for an async analysis flow. The description never says when to prefer this over analysis_get or transcript_get, nor when re-running versus reading cached results is appropriate.

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