Skip to main content
Glama

build_video

Creates a finished social video from ordered clips by adding transitions, voiceover, captions, music, title and end cards, then exports it in platform-ready formats.

Instructions

ONE call for a finished video. clips: video names in order, or {"video", "start", "end", "speed"} to cut/speed one. transition: cut | fade | crossfade. shape: "9:16" (Shorts/Reels/TikTok) | "1:1" | "4:5" | "16:9". voice: the words to say (or {"text", "voice": andrew|emma|ava|brian|es|pt..., "engine": edge|local, "sample"} or {"audio": file}). captions: "auto" (timed to the voice) or your own text. music: a music file path (or {"file", "volume"}); it gets quieter under the voice. title: text for a card at the start. end_card: text for the last card (true = "Follow for more"). export: shorts | reels | tiktok | facebook | youtube | x | square (right size and format to post). Only the final video stays in the gallery.

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": {
      "clips": "<clips>"
    },
    "name": "build_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
clipsYes
musicNo
shapeNo
titleNo
voiceNo
exportNo
captionsNo
end_cardNo
transitionNocrossfade

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations only declare readOnly=false, destructive=false and openWorld=false, so the safety profile is thin. The description adds real behavioral context beyond that: 'Only the final video stays in the gallery' (intermediate artifacts are discarded), music 'gets quieter under the voice' (auto-ducking), captions timed to the voice, and export presets producing platform-correct sizing/format. It stops short of saying what the call returns or how long it takes.

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?

Front-loaded with the core value proposition, then one dense line per parameter — no filler. It is telegraphic in places ('true = "Follow for more"', bare 'square' in the export list), which trades a little readability for compactness but never wastes a sentence.

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

Completeness4/5

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

For a 9-parameter pipeline tool with no output schema and minimal annotations, the description covers inputs and side effects (gallery retention) well enough to call it correctly. The notable remaining gap is the return value — whether an agent gets a job id, a file path, or a status to poll — plus no hint about failure modes or duration.

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

Parameters5/5

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

Schema coverage is 0% and there are no enums, so the description carries the full burden — and it does: it gives the clips array element formats (plain name vs {video,start,end,speed}), the transition values, shape values mapped to platforms, the voice input shapes including named voices and engines, captions 'auto' vs custom text, music file-or-object with volume, and the export targets. This meaning is entirely absent from the raw schema.

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?

Opening line 'ONE call for a finished video' names the resource (video) and its key distinguishing trait: it composes the whole pipeline rather than one edit step. That implicitly separates it from granular siblings like add_music, add_voice, fade, end_card and export, though no sibling is named explicitly.

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 'ONE call' framing tells the agent to reach for this when a complete video is wanted, and the granular siblings cover single-step edits. There is no explicit when-not guidance, no prerequisite statement (e.g. that clips must already exist in the gallery), and no indication of cost or runtime.

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