yt_video_detailsGet detailed information about one or more YouTube videos including title, description, channel, duration, view/like/comment counts, and tags.
| Name | Required | Description | Default |
|---|---|---|---|
| _apiKey | Yes | YouTube Data API v3 key from Google Cloud Console | |
| video_id | Yes | Video ID or comma-separated list of video IDs (max 50) |
| Name | Required | Description | Default |
|---|---|---|---|
| videos | Yes | Array of video detail objects |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "videos": {
+ "description": "Array of video detail objects",
+ "items": {
+ "properties": {
+ "category_id": {
+ "description": "YouTube category ID",
+ "type": "string"
+ },
+ "channel_id": {
+ "description": "Channel ID",
+ "type": "string"
+ },
+ "channel_title": {
+ "description": "Channel title",
+ "type": "string"
+ },
+ "comment_count": {
+ "description": "Total comment count",
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "definition": {
+ "description": "Video definition (sd or hd)",
+ "type": "string"
+ },
+ "description": {
+ "description": "Video description",
+ "type": "string"
+ },
+ "duration": {
+ "description": "ISO 8601 duration string (e.g., PT5M30S)",
+ "type": "string"
+ },
+ "id": {
+ "description": "Video ID",
+ "type": "string"
+ },
+ "like_count": {
+ "description": "Total like count",
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "published_at": {
+ "description": "ISO 8601 publish date",
+ "type": "string"
+ },
+ "tags": {
+ "description": "Array of video tags",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "thumbnail": {
+ "description": "Default thumbnail URL",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "title": {
+ "description": "Video title",
+ "type": "string"
+ },
+ "view_count": {
+ "description": "Total view count",
+ "type": [
+ "number",
+ "null"
+ ]
+ }
+ },
+ "required": [
+ "id",
+ "title",
+ "description",
+ "channel_title",
+ "channel_id",
+ "published_at",
+ "tags",
+ "category_id",
+ "thumbnail",
+ "duration",
+ "definition",
+ "view_count",
+ "like_count",
+ "comment_count"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "videos"
+ ],
+ "type": "object"
+}Input schema / examplesAdded value: +[
+ {
+ "_apiKey": "your-youtube-api-key",
+ "video_id": "dQw4w9WgXcQ"
+ },
+ {
+ "_apiKey": "your-youtube-api-key",
+ "video_id": "dQw4w9WgXcQ,9bZkp7q19f0"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint, providing clear safety and behavior signals. The description adds value by listing the types of fields returned (e.g., title, duration, counts), which supplements the annotations without contradicting them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence of 22 words that efficiently states the tool's purpose and key fields. Every word contributes, with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (2 params with 100% schema coverage, rich annotations, and an output schema), the description is complete enough. It summarizes the core functionality, while the schema and annotations handle parameter and behavioral details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with each parameter already having a clear description (e.g., video_id: 'Video ID or comma-separated list... max 50'). The tool description does not add additional parameter semantics beyond the schema, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get') and resource ('detailed information about one or more YouTube videos'), and lists example fields (title, description, channel, etc.). This clearly distinguishes it from sibling tools like yt_search (searching) and yt_channel_details (channel info).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for fetching video metadata but does not explicitly state when to use this tool vs alternatives (e.g., yt_search for finding videos, yt_video_comments for comments). No when-not or exclusionary criteria are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The five yt_* tools are distinct, but the majority of the set is dominated by overlapping Pipeworx tools: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-identical entry points, and the multiple polymarket_* tools cover closely related edge/arbitrage/fill-risk territory. An agent could easily select the wrong one.
Most names use lowercase snake_case, but conventions are mixed: yt_* and polymarket_* are prefix-scoped, pipeworx_* mixes verb-first and noun-first names, and there are standalone verbs like remember, recall, and forget. The server is named Youtube, yet the bulk of tools follow unrelated Pipeworx/Polymarket naming.
36 tools is heavy for a server named Youtube, and only 5 actually address YouTube functionality. The remaining 31 tools cover unrelated data-research and prediction-market features, making the surface bloated and off-purpose.
The YouTube subset covers search, channel info, channel videos, video details, and comments, which handles basic read-only queries. Missing playlists, captions/transcripts, and subscription/upload actions leave notable gaps for a YouTube-focused server.