Skip to main content
Glama

narrate_scenes

Generate one narration audio file per scene with exact seconds, frame timings, and optional word-level captions for syncing video timelines.

Instructions

Voice a list of scenes (strings or {id, text}) as one audio file per scene and return each scene's exact seconds, durationInFrames and startFrame at the given fps, plus a narration.json manifest. captions=true also writes word-level captions.json in Remotion's Caption format. Unchanged scenes are cached and cost nothing on re-runs.

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": {
      "scenes": "<scenes>"
    },
    "name": "narrate_scenes"
  }
}

Input Schema

NameRequiredDescriptionDefault
fpsNo
modelNoexpressive
scenesYes
captionsNo
voice_idNo
output_dirNo
reference_textNo
reference_audio_urlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations at all, the description does substantial work: it discloses write side effects (audio files per scene, narration.json, optional captions.json), the return payload (exact seconds, durationInFrames, startFrame), and a cost/caching behavior on re-runs. It omits failure modes and overwrite semantics for output_dir, keeping it just 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.

Conciseness4/5

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

Three dense sentences, front-loaded with the core action and output shape, then optional captions, then caching. No filler, though packing multiple behaviors per sentence makes it slightly harder to scan than a bulleted form.

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?

Returns are well explained, which matters given there is no output schema, and the caching/cost note is valuable given no annotations. However, for an 8-parameter tool with 0% schema coverage, the five undocumented parameters (especially voice cloning via reference_text/reference_audio_url) leave a real gap before an agent can call it confidently.

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 0% across 8 parameters, so the description must compensate and largely does not. It clarifies only scenes (string or {id, text}), fps, and captions, leaving model (what values besides 'expressive'?), voice_id, output_dir, reference_text, and reference_audio_url entirely undocumented anywhere.

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 leads with a specific verb and resource — 'Voice a list of scenes' — and states the concrete artifacts produced (one audio file per scene, narration.json). It implicitly differentiates from siblings like speak by being batch/timing-oriented, but never names an alternative, so it falls short of full sibling differentiation.

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 inferable rather than stated: the fps/frame-timing framing implies this is for building Remotion video timelines, and the caching note signals suitability for iterative re-runs. There is no explicit 'use this instead of speak when…' guidance or any exclusion, so an agent must infer the selection criteria.

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

Deploy Server

Other Tools