ThumbnailMaker

Make three to test

make_three_to_test

Makes three concepts on three different angles chosen to fit the video (among emotion, object, contrast, result, process, place, mood), ready for YouTube's own A/B test. Three thumbnails (30 credits); a concept that fails is refunded. First call without confirm to get the price. Studio plan.

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": "make_three_to_test"
  }
}

Input Schema

Name	Required	Description
`text`	No	Up to about five words, drawn exactly as typed
`style`	No	One of: Shocked Reaction, Before/After, Expressive Close-up, Tech / Review, Blocky World, Victory Moment, Podcast, Versus, Horror / Mystery, VR Chase, Sports Action, Tactical Shooter, Comic / Anime, Cute 3D
`format`	No	16:9 for videos, 9:16 for Shorts
`prompt`	No	What the thumbnail shows. Describe people generically; real people are refused.
`confirm`	No	Leave out on the first call to get the price. Send true only after the person agreed to it.
`quoteId`	No	The quoteId the price call returned; required with confirm: true.
`videoUrl`	No	A youtube.com or youtu.be video link
`brandKitId`	No	An id from list_brand_kits

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare this is a non-read-only, open-world, non-idempotent, non-destructive operation, so the bar is lower. The description adds real value beyond them: 30-credit cost, refund policy for a failed concept, and the two-step price/confirm flow. It still omits what a partial failure looks like and how credits are actually charged/timed.

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-loads the core action ('Makes three concepts...'), then cost, refund, and call sequence in short clauses. Dense but each sentence carries information; minor run-on structure costs it the top mark.

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?

Covers purpose, cost, refund, plan gate, and the two-step confirm flow, which is what an agent needs to invoke it safely. With no output schema, it could say more about what the price call returns (quoteId) and which inputs are truly required, keeping it from a 5.

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 description coverage is 100%, so both enum and free-text parameters are already well documented, making 3 the baseline. The description reinforces the confirm/quote flow but adds no syntax or format detail not already in the schema; the 'angles' list is not a parameter and adds little to param understanding.

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?

States a specific verb and resource: it makes three concepts on three different angles as three thumbnails, explicitly framed for YouTube A/B testing. The 'three' and 'A/B test' framing clearly distinguishes it from the single-output generate_thumbnail sibling, though the sibling is never named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete workflow guidance: 'First call without confirm to get the price,' and the schema/description pair tells the agent to send confirm only after agreement, plus a 'Studio plan' prerequisite. It does not explicitly compare against generate_thumbnail or check_thumbnail, so selection between the generation tools is left partly to inference.

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

All ThumbnailMaker tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?