Skip to main content
Glama

Draft a video script

draft_video

Write a video's script and scenes WITHOUT rendering or charging, so the user can read and change it first. Returns draftId, the scenes (narration + visual prompt each) and the exact render price. Free, but it runs the script writer once: needs a balance that can pay for a render and is limited to 20 drafts per hour. Then: show it → update_draft / revise_scene → render_draft only after the user approves the price. A new account with no credits that has not had its free first video gets it here instead of an error: watermarked, labelled AI-generated, up to 30 seconds, standard voice, one per account, subject to the day's availability. For that video the draft is up to 30 seconds (about 80 words) and 3 drafts per hour. Set prompt_handling to "as_written" to use my words exactly. If the model refuses a scene, it fails instead of being reworded. Each scene says who wrote its picture text (promptSource). Use create_video instead when no review is wanted. Requires the "video:create" scope.

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": {
      "topic": "<topic>"
    },
    "name": "draft_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoOptional title (defaults to the topic).
topicYesWhat the video is about; the script is written from it.
artStyleNoOptional art style (default AUTOSHORTS).
durationNoTarget length in seconds (default 30; 90 needs a paid plan).
languageNoOptional BCP-47 narration language, e.g. "en", "vi".
prompt_handlingNo"as_written": Use my words exactly. If the model refuses a scene, it fails instead of being reworded. "assist" (default): the product may reword picture text, as before.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / prompt_handling
      Added value: +{
      +  "description": "\"as_written\": Use my words exactly. If the model refuses a scene, it fails instead of being reworded. \"assist\" (default): the product may reword picture text, as before.",
      +  "enum": [
      +    "assist",
      +    "as_written"
      +  ],
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) it discloses that the script writer runs once, that a payable balance is required, a 20-drafts-per-hour limit, and the no-credits free-first-video path with its watermarks, 30-second cap, 3-drafts-per-hour limit and per-account restriction. It also states the failure mode under prompt_handling="as_written" (refusal fails rather than rewords) and that each scene reports promptSource — none of which is derivable from the structured fields.

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 core constraint (no render, no charge, review first) is front-loaded and every sentence carries operational information. The free-tier sentence is long and clause-stacked (watermarked, labelled, 30s, standard voice, one per account, availability), which slows parsing but is not padding.

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

Completeness5/5

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

For a non-idempotent, open-world creation tool with no output schema, the description covers cost, preconditions, rate limits, return payload (draftId, scenes with narration and visual prompt, exact render price), the downstream workflow, and the free-tier edge case. An agent has enough to call it and to explain the result to a user.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description still adds meaning by tying the free-tier path to a concrete duration ("up to 30 seconds (about 80 words)") and by restating the exact-wording contract of prompt_handling, which is the parameter most likely to be misused. It does not add much for title, artStyle or language, which the schema already covers.

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?

"Write a video's script and scenes WITHOUT rendering or charging" names a specific verb and resource plus the boundary that distinguishes it from render_draft and create_video. The parenthetical payoff ("so the user can read and change it first") tells the agent why this exists as a separate step.

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 an explicit workflow chain: show it → update_draft / revise_scene → render_draft only after the user approves the price. It also names the alternative and the condition that selects it ("Use create_video instead when no review is wanted"), so an agent can route correctly without guessing.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources