Vee3

youtube.search

Search public YouTube content by keyword or phrase.

Returns matching result cards, estimated result count, and spelling suggestions.

Use filter parameters to apply multiple YouTube search filters:

upload_date: Last hour, Today, This week, This month, This year
content_type: Video, Channel, Playlist, Movie
duration: Under 4 minutes, 4 - 20 minutes, Over 20 minutes
features: Live, 4K, HD, Subtitles/CC, Creative Commons, 360°, VR180, 3D, HDR, Location, Purchased (multiple allowed)
sort_by: Relevance, Upload date, View count, Rating

Filter values are matched case-insensitively. Only one option per group applies except features, which accepts multiple labels.

When a requested filter cannot be applied, the API returns the best-effort results available so far and includes unappliedFilters with the labels that were skipped.

Use cursor with the same query to paginate: pass cursorNext from a prior response. Filter parameters and cursor cannot be combined.

Check didYouMean when the query may be misspelled.

Cost = 20 tokens.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	Search keywords or phrase.
`cursor`	No	Pagination cursor from cursorNext.
`sort_by`	No	Sort order. One of: Relevance, Upload date, View count, Rating.
`duration`	No	Duration filter. One of: Under 4 minutes, 4 - 20 minutes, Over 20 minutes.
`features`	No	Feature filters. Multiple allowed. Each value must be one of: Live, 4K, HD, Subtitles/CC, Creative Commons, 360°, VR180, 3D, HDR, Location, Purchased.
`language`	No	Language code for localized results (for example en).	en
`location`	No	Country code for localized results (for example US).	US
`upload_date`	No	Upload date filter. One of: Last hour, Today, This week, This month, This year.
`content_type`	No	Content type filter. One of: Video, Channel, Playlist, Movie.

Output Schema

TableJSON Schema

Name	Required	Description
`contents`	No	Search result entries for the current page. Video entries include a type field and nested video object.
`cursorNext`	No	Cursor for the next results page, when available.
`didYouMean`	No	Suggested corrected query when the search may be misspelled.
`estimatedResults`	No	Approximate total number of matching results.
`unappliedFilters`	No	Requested filter labels that could not be applied. Present only when at least one filter was skipped.

Schema Changelog

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

Changed2 schema fields changedJun 21, 2026

removedOutput schema / $defs / YoutubeSearchResponseUnappliedFiltersItem

Removed value: -{
-  "additionalProperties": true,
-  "properties": {
-    "label": {
-      "anyOf": [
-        {
-          "type": "string"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "default": null,
-      "description": "Filter label that could not be applied.",
-      "title": "Label"
-    }
-  },
-  "title": "YoutubeSearchResponseUnappliedFiltersItem",
-  "type": "object"
-}

changedOutput schema / properties / unappliedFilters / anyOf

Previous value: -[
-  {
-    "items": {
-      "$ref": "#/$defs/YoutubeSearchResponseUnappliedFiltersItem"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

First observedJun 18, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Discloses multiple non-obvious behaviors: case-insensitive filter matching, restriction of one value per group except features, best-effort results with unappliedFilters, inability to combine filters and cursor, and didYouMean hints. These go well beyond the schema.

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?

The description is well-structured with bullets, front-loaded with purpose, and every sentence adds value. Despite length, it remains scannable and free of redundancy.

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?

For a complex search tool with output schema, the description covers return values, filter options, pagination, error behavior, and cost. It provides a complete operational picture without needing the output schema to explain behavior.

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?

The schema covers all 9 parameters at 100%, but the description adds crucial relational semantics: only one option per filter group except features, filter/cursor incompatibility, and the unappliedFilters mechanism. This supplements the schema meaningfully.

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's function: 'Search public YouTube content by keyword or phrase.' It distinguishes itself from sibling tools like youtube.channel_search and youtube.search_autocomplete, and outlines the returned data types.

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?

Provides clear guidance on filter usage, pagination with cursor, and error handling. However, it does not explicitly mention when to choose this tool over alternatives like youtube.channel_search, so it falls short of a 5.

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

All Vee3 tools Inspect

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

A4.1/5.0

Disambiguation5/5

Each tool has a distinct purpose, further clarified by group prefixes and clear descriptions. Within each group, tools perform different operations (e.g., domains.lookup vs. domains.whois vs. domains.rdap) with no ambiguity.

Naming Consistency5/5

All tools follow a consistent group.tool_name pattern using snake_case. The naming is predictable and uniformly applied across all groups.

Tool Count4/5

78 tools is high, but the server aggregates multiple distinct API domains (11 groups). Each group has a reasonable number of tools, typically under 10, with TikTok having 17. The count reflects breadth, not bloat.

Completeness5/5

Each domain's tool set covers the primary expected operations (e.g., search, details, reviews, metrics, user info). There are no obvious gaps for read-only analytical use; features like posting are likely out of scope.

youtube.search

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

TDQS

Resources