Skip to main content
Glama

find_best_thumbnails

Read-only

Read what the signed-in user's BEST-performing YouTube thumbnails on their own channel have in common (the on-thumbnail text, faces, colors, layout), to reveal the pattern behind their proven packaging. Call this when the user asks what makes their best thumbnails work, what their winning thumbnails share, or wants to understand their thumbnail pattern. This is only about the pattern ACROSS their top thumbnails. To generate or score packaging for a specific or new video (title options, thumbnail text, or reviewing one video's title/thumbnail), use package_video. Needs no input: it reads their real connected YouTube channel directly. Never ask the creator anything first, not for context, not for a link, not for a title you could look up; call it immediately.

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": "find_best_thumbnails"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

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

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered; the description adds the important operational facts that it reads the real connected YouTube channel and requires no input, plus the unusual directive not to ask the creator for context or a link. What it does not disclose is return shape or behavior when no channel is connected or too few videos exist — a real gap for an open-world read.

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 core purpose, then scope contrast, then the sibling alternative, then the no-input directive — a sound ordering. It is somewhat verbose at the tail: 'Needs no input' and the long 'Never ask the creator anything first, not for context, not for a link, not for a title you could look up' restate the same instruction twice.

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?

For a zero-parameter, read-only analysis tool with no output schema, the description covers what is analyzed (on-thumbnail text, faces, colors, layout), the scope boundary, and the calling precondition. It stops short of describing the shape of the returned pattern summary or failure modes such as an unconnected channel, which would complete it.

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?

There are zero parameters, so the baseline is 4. The description reinforces this with 'Needs no input' and 'Never ask the creator anything first', which is the only parameter-relevant semantic an agent needs here — no argument names or formats to explain.

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 resource — reads the common traits (text, faces, colors, layout) across the signed-in user's top-performing thumbnails on their own channel — and immediately contrasts the scope with 'pattern ACROSS their top thumbnails' vs. single-video work. It names the sibling it is not (package_video) so an agent can separate the two without opening either 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 explicit trigger phrasing ('what makes their best thumbnails work', 'what their winning thumbnails share', 'understand their thumbnail pattern') and an explicit exclusion routing to package_video for generating or scoring packaging for a specific or new video. When-to-use, when-not-to-use, and the alternative are all present.

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