Skip to main content
Glama

draft_script

Read-only

Draft a video SCRIPT for the signed-in user, in their own voice, built from what already converts on their own YouTube channel and engineered to fix the opening where they lose viewers. For a long-form video it returns two or three hook options, a beat-by-beat outline, key lines, a CTA, and a suggested title; for a Short, a tight word-for-word script. Call this when the user asks to write, draft, or outline a script (or a hook, intro, or outline) for a video or idea. Pass topic (what the video is about) and optionally format ('short' or 'long'). Klyf Pro only. For titles and thumbnails use package_video; to judge whether an idea is worth making use evaluate_idea; to brainstorm ideas use suggest_ideas.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "draft_script"
  }
}

Input Schema

NameRequiredDescriptionDefault
ideaNo
titleNoThe title already agreed for the video, if there is one
topicNoWhat the video is about
formatNoWhether it is a Short or a long-form video; defaults to long-form

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them: the script is grounded in the user's own channel performance data, targets the opening drop-off, and returns different artifacts for long-form (multiple hooks, beat outline, key lines, CTA, title) versus a Short (word-for-word). It also discloses the Klyf Pro entitlement requirement. It does not cover generation latency, whether drafts persist, or regeneration behavior, which keeps it from 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?

Front-loaded with what it does and what it returns before the routing guidance and parameter notes, and nearly every clause carries information. The description is dense but well ordered; the only redundancy is restating the format default that the schema already declares.

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?

With no output schema and no required parameters, the description carries the burden of describing returns and it does so precisely for both formats. It also covers entitlement gating and sibling alternatives, leaving nothing an agent needs in order to select and call it correctly.

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 75%, so the baseline is 3. The description explains `topic` and `format` (including the long-form default, which duplicates the schema), but says nothing about `idea` — the one parameter with no schema description — nor about how `topic`, `title`, and `idea` interact when supplied together.

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?

Uses a specific verb ("Draft") with a specific resource ("video SCRIPT for the signed-in user"), then states the differentiating input (built from what converts on their own channel) and the differentiating output shape per format. An agent can distinguish this from package_video, evaluate_idea, and suggest_ideas without opening any 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?

Gives an explicit trigger phrase set ("write, draft, or outline a script (or a hook, intro, or outline)") and names three sibling tools with the conditions that select them instead. Nothing about routing is left to inference.

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