Skip to main content
Glama

Write a short-form video script

draft_video_script
Read-only

Use this when the user wants a script for a short vertical video, such as "write a 25-second TikTok and Reels script about our new app". Pass the topic, with the facts to use, and 1 to 4 platforms from tiktok, youtube_shorts, instagram_reels, x_video; say in the topic if an AI-generated presenter or voice will be used. Returns a script on a fixed clock (hook 0 to 3 seconds, body 4 to 20 seconds, call to action by about 25 seconds) with voiceover, on-screen text and visuals, a timing check, a caption for each platform checked against its rules, each platform's official video length limit with its source, and an ai_disclosure block naming the AI label that applies when the script declares an AI-generated person or voice. Uses only the facts given. It does not publish, make the video, clone voices or write for fake-identity accounts.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "topic": "Our new budgeting app, Penny Jar. It sorts card spending into envelopes by itself and warns you 3 days before a bill is due.",
      "platforms": [
        "tiktok",
        "instagram_reels"
      ]
    },
    "name": "draft_video_script"
  }
}

Input Schema

NameRequiredDescriptionDefault
toneNoOptional voice, such as "friendly and plain" or "dry humour".
topicYesWhat the video is about, with the facts to use. Say if it will use an AI-generated presenter or voice, so the right label is named.
platformsYesWhere the video will be posted: tiktok, youtube_shorts, instagram_reels, x_video.

Output Schema

NameRequiredDescriptionDefault
as_ofYes
postsYes
noticeYes
scriptYes
sourceYes
statusYes
messageNo
rules_as_ofYesDate the video limits and label policies were last read (2026-10-01).
ai_disclosureYes
platform_limitsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "platforms": [
      +      "tiktok",
      +      "instagram_reels"
      +    ],
      +    "topic": "Our new budgeting app, Penny Jar. It sorts card spending into envelopes by itself and warns you 3 days before a bill is due."
      +  }
      +]
  2. Changed1 schema field changed
    • removedOutput schema / properties / note_from_openkrill
      Removed value: -{
      -  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
      -  "type": "string"
      -}
  3. Changed1 schema field changed
    • addedOutput schema / properties / note_from_openkrill
      Added value: +{
      +  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
      +  "type": "string"
      +}
  4. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say readOnlyHint=true and non-destructive; the description adds substantive behavior well beyond that: the fixed clock structure (hook 0-3s, body 4-20s, CTA by ~25s), the timing check, per-platform caption rule validation, platform length limits with sources, and the ai_disclosure block conditioned on an AI presenter/voice. It also states the tool uses only the facts given, which is a real behavioral constraint.

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 trigger and example, then the input contract, then the output contract, then the exclusions — a sensible order. It is dense and runs long, with the return-value enumeration packing many clauses into two sentences, but no sentence is filler.

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 3-parameter generator with an output schema and read-only annotations, the description is more than complete: it covers inputs, output composition, platform-specific validation, and limits of responsibility. Nothing an agent needs to invoke it correctly is missing.

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 baseline is 3, but the description adds value: it explains why the topic must declare an AI presenter/voice (so the right label is named) and enumerates the valid platform set inline. The optional tone parameter is left entirely to the schema.

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?

States a specific verb+resource (draft a short-form vertical video script) with scope detail, and explicitly separates it from siblings by declaring it does not publish, make the video, or write for fake-identity accounts. An agent can distinguish it from draft_posts, draft_tiktok_slides and launch_video 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?

Opens with an explicit trigger ('Use this when the user wants a script for a short vertical video') plus a concrete example utterance, then names what to pass. It also names exclusions (no publishing, no video production, no voice cloning, no fake-identity accounts), so both when-to-use and when-not-to-use are covered.

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.