Skip to main content
Glama

find_best_videos

Read-only

Find the signed-in user's best-performing YouTube videos on their own channel, ranked several ways: which produced the most subscribers, the most views, held viewers longest (retention), earned the most total watch time, got clicked most often when shown, and which sparked the most comments, with their titles, so the pattern behind what works becomes clear. Call this when the user asks what is working, which videos performed best, what got them subscribers, which video had the best retention or held viewers longest, which got the most watch time, which video or thumbnail got the most clicks or the best click-through rate, which video got the most comments, what their winners have in common, or what to make more of. 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_videos"
  }
}

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

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds real behavior beyond them: it reads the user's actual connected channel rather than accepting IDs, requires no input at all, and must be called without clarifying questions. It does not mention limits such as channel-size constraints, empty-channel behavior, or ranking tie-breaking, which keeps it short of 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.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the metric enumeration is a long run-on list with visible redundancy — "best retention or held viewers longest" and "most clicks or the best click-through rate" restate the same idea in successive clauses. The trigger list repeats the same metrics a second time, so the description roughly doubles in length without adding information.

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?

With no parameters and no output schema, the description carries the burden of explaining what comes back, and it does so (videos, titles, several ranking dimensions). It stops short of describing result shape, ordering, or what happens on a channel with too little data, but is sufficient for an agent to call it correctly.

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?

Zero parameters, so the baseline is 4, and the description explicitly confirms "Needs no input" which matches the empty schema. No additional parameter meaning is needed or possible.

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 — find the signed-in user's best-performing YouTube videos on their own channel — and immediately enumerates the ranking axes (subscribers, views, retention, watch time, CTR, comments) plus the returned titles. This clearly separates it from generic siblings like find_videos or analyze_video.

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 a long, explicit list of trigger questions ("what is working", "which video had the best retention", "what their winners have in common") and a strong negative instruction not to ask the creator for context or links before calling. It never names the sibling tools it supersedes (e.g., find_videos, find_best_thumbnails), so the routing against alternatives is implied rather than explicit.

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