Skip to main content
Glama

analyze_video

Read-only

Deep dive on ONE specific YouTube video of the signed-in user's own channel, to explain how it did and why. Returns that video's performance versus their usual, where viewers dropped off, how it was found, and what its comments say. Call this whenever the user asks about a SINGLE video: how a video did or performed, why a video flopped, bombed, tanked, underperformed, or got few views, why a video did well, blew up, popped off, or went viral, what happened with a video, or to break down, analyze, review, or explain one video. Also for 'my last video', 'my latest video', 'my newest upload', or a video named by its title. If the user names the video (a title or part of one), pass it as video; leave video empty to analyze their most recent upload. A vague reference with no title (like 'that video', 'this video', 'the video') also means their most recent upload: analyze it, do not stop to ask which one. For the whole channel at once use audit_channel; for the ranked list of what to fix use diagnose_channel; for the best videos across the channel use find_best_videos. 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": "analyze_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNo
videoNoThe video's title (or part of it); omit for the most recent upload

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
Behavior5/5

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

Beyond readOnlyHint and openWorldHint, the description discloses that the tool reads the user's real connected YouTube channel directly and explains the substantive analysis areas it returns. It also defines deterministic fallback behavior when no usable title is supplied, giving the agent a clear picture of what invoking it will do.

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 and returned analysis are front-loaded, and the sibling-routing sentence is compact and useful. The long catalog of slang synonyms and repeated latest-video and no-clarification instructions make the description substantially more repetitive than necessary.

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 simple read-only tool without an output schema, it covers scope, data source, result categories, selection triggers, default behavior, and alternatives. The unexplained `title` parameter and potentially confusing “Needs no input” wording leave a small but real invocation gap.

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?

The description adds useful invocation rules for `video`: pass a full or partial title, omit it for the latest upload, and treat vague references as the latest upload without asking. However, it never explains the separate `title` input, and “Needs no input” is less precise than saying all inputs are optional, so the 50% schema coverage is not fully compensated.

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?

The opening sentence specifies a diagnostic deep dive on one YouTube video from the signed-in user's own channel, including the goal of explaining how and why it performed as it did. It concretely lists relative performance, audience drop-off, discovery sources, and comment themes, while later sibling routing further sharpens its scope.

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?

It gives extensive, explicit triggers for single-video questions, including named, latest, and vaguely referenced videos, and prescribes the latest-upload default instead of asking for clarification. It also distinguishes whole-channel audits with audit_channel, ranked fixes with diagnose_channel, and channel-wide best-video searches with find_best_videos.

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