Skip to main content
Glama

Youtube

by io.github.pipeworx-io

Yt Search

yt_search
Read-onlyIdempotent

Search YouTube for videos, channels, or playlists. Returns snippet info including title, description, channel, thumbnails, and publish date.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeNoResource type to search: "video", "channel", or "playlist" (default: "video")
orderNoSort order: "date", "rating", "relevance", or "viewCount" (default: "relevance")
queryYesSearch term
_apiKeyYesYouTube Data API v3 key from Google Cloud Console
channel_idNoFilter results to a specific channel ID
max_resultsNoNumber of results to return (default 10, max 50)
published_afterNoFilter results published after this ISO 8601 date (e.g. "2024-01-01T00:00:00Z")

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultsYesArray of search result items
total_resultsYesTotal number of search results available

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "results": {
+      "description": "Array of search result items",
+      "items": {
+        "properties": {
+          "channel_id": {
+            "description": "Channel ID",
+            "type": "string"
+          },
+          "channel_title": {
+            "description": "Channel title",
+            "type": "string"
+          },
+          "description": {
+            "description": "Resource description",
+            "type": "string"
+          },
+          "id": {
+            "description": "Video, channel, or playlist ID",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "kind": {
+            "description": "Resource kind (youtube#video, youtube#channel, etc.)",
+            "type": "string"
+          },
+          "published_at": {
+            "description": "ISO 8601 publish date",
+            "type": "string"
+          },
+          "thumbnail": {
+            "description": "Default thumbnail URL",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "description": "Resource title",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "kind",
+          "title",
+          "description",
+          "channel_title",
+          "channel_id",
+          "published_at",
+          "thumbnail"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total_results": {
+      "description": "Total number of search results available",
+      "type": "number"
+    }
+  },
+  "required": [
+    "total_results",
+    "results"
+  ],
+  "type": "object"
+}
  2. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "_apiKey": "your-youtube-api-key",
+    "query": "machine learning tutorial"
+  },
+  {
+    "_apiKey": "your-youtube-api-key",
+    "max_results": 20,
+    "order": "viewCount",
+    "published_after": "2024-01-01T00:00:00Z",
+    "query": "Python programming",
+    "type": "video"
+  }
+]
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds useful context about returned snippet fields, which is sufficient beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

Two sentences, no wasted words. The action and key result are front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the schema coverage, examples, output schema, and rich annotations, the description is complete enough for an agent to understand the tool's behavior and use it correctly.

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?

All 7 parameters are fully described in the input schema (100% coverage). The description does not add significant meaning beyond what the schema and examples provide.

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 description clearly states the tool searches YouTube for videos, channels, or playlists, and lists the returned snippet info. It is distinct from sibling tools like yt_channel_details or yt_video_details.

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

Usage Guidelines3/5

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

The description implies search functionality but does not explicitly guide when to use this tool vs sibling tools like yt_channel_details. No when-not-to-use or alternatives are mentioned.

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

All Youtube toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation3/5

There is meaningful overlap among the ask_pipeworx, deep_research, validate_claim, and polymarket_* tools, but the descriptions do draw fairly clear boundaries between them. The five yt_* tools are distinct and easy to tell apart, though the unrelated Pipeworx cluster makes the overall set feel muddier than it should.

Naming Consistency3/5

Most tools use readable snake_case, and there are coherent prefixes like yt_ and polymarket_, but the set mixes bare verbs (remember, recall, forget, subscribe), noun-style names (entity_profile, deep_research), and API-like names (ask_pipeworx, generate_llms_txt). The pattern is not chaotic, but it is inconsistent across the set.

Tool Count2/5

36 tools is well above the typical well-scoped range, and the vast majority are unrelated to the server's stated 'Youtube' identity. The actual YouTube surface is only five tools, while 31 tools belong to a different Pipeworx/Polymarket domain.

Completeness2/5

For a YouTube-focused server, the yt_* tools cover search, channel info, video details, and comments, but miss obvious surfaces like playlists, transcripts, subscriptions, uploads, and video updates. The large non-YouTube tool collection does not fill these gaps; it only makes the server feel mis-scoped.

Resources