Skip to main content
Glama

Create title and thumbnail options

create_generation
Idempotent

Make title and thumbnail options for the user's video: use when they ask for thumbnails, titles or packaging options. Start a durable VoxTale generation from one topic, script, or transcript; for saved material, read it with get_project and pass projectId. Rendered runs need a face choice first (show_face_picker). Omit mode (or use full) for rendered thumbnails; mode concept returns ranked titles, hooks, angles and text thumbnail briefs plus artDirection (composition, typography, color treatment, lighting and background) without rendering images. Both modes consume the same generation allowance. Creates a project unless projectId is supplied; with projectId the niche follows that project's channel. To re-run with adjustments, copy config from get_generation and change what the user asked for. Consumes account allowance once accepted. Use only at the user's request. Supply one unique idempotencyKey and reuse that key and identical input on retries. Returns pending status; poll get_generation. Does not publish to YouTube.

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": {
      "idempotencyKey": "<idempotencyKey>",
      "material": "<material>"
    },
    "name": "create_generation"
  }
}

Input Schema

NameRequiredDescriptionDefault
cellNo
modeNofull (default) renders thumbnails; concept returns text packaging briefs without image rendering.
styleNo
titleNo
facelessNo
materialYes
pipelineNo
directionNo
projectIdNo
refAssetIdsNo
faceAssetIdsNo
patternBreakNo
idempotencyKeyYes
styleRefAssetIdsNo

Output Schema

NameRequiredDescriptionDefault
modeNo
errorNo
runIdYes
configNo
statusYes
webUrlYes
optionsNo
progressNo
projectIdYes
allFlaggedNo
packagingUrlNo
pollAfterSecondsNo
artifactExpiresAtNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare idempotentHint=true, openWorldHint=true and destructiveHint=false, but the description adds substantial non-obvious behaviour: both modes consume the same allowance, allowance is consumed once accepted, a project is created unless projectId is supplied, niche follows the project's channel, the call returns pending status and must be polled via get_generation, and it does not publish to YouTube. The idempotency contract (one unique key, reused with identical input on retries) is spelled out in operational terms rather than left to the hint.

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 purpose and trigger conditions before the operational detail, and nearly every sentence carries a distinct constraint (face picker, allowance, polling, no publishing). It is dense and somewhat run-on at this length, but little of it is filler given the tool's complexity.

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?

Return values are covered by an output schema, yet the description still usefully notes the pending status and the polling step, which an agent needs to sequence correctly. For a mutation tool with 14 parameters and nested material, the main residual gap is the undescribed optional styling/enum parameters (pipeline, patternBreak, faceless, reference asset arrays).

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?

With only 7% schema description coverage across 14 parameters, the description does the heavy lifting for a few key ones: mode (full vs. concept and what concept returns, including artDirection contents), material kinds (topic, script, transcript), projectId (creates a project if omitted; niche follows the channel), and idempotencyKey. However, cell, style, title, faceless, patternBreak, pipeline, direction, refAssetIds and styleRefAssetIds receive no explanation anywhere, leaving the majority of the surface undocumented.

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 and artefact set ('Make title and thumbnail options for the user's video') and immediately splits the behaviour into the two modes it produces (rendered thumbnails vs. ranked titles/hooks/angles with artDirection). This is clearly distinguishable from siblings like edit_thumbnail, get_thumbnail, and get_generation_options.

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?

Explicitly names the triggering user request ('when they ask for thumbnails, titles or packaging options'), routes saved material to get_project, requires show_face_picker before rendered runs, explains when to choose mode concept vs. omitting mode, and points at get_generation for re-runs with adjustments. It also sets a hard precondition: 'Use only at the user's request.'

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