YouTube Playlist MCP

Preview playlist

preview_playlist

Read-only

Builds a numbered playlist preview from search results, remembers excluded videos, and lets you review and approve the list before creating the playlist.

Instructions

Build (or rebuild) a numbered playlist preview from a search. Exclusions are remembered across calls for the same search_id. Show the returned markdown to the user and ask for approval or changes before create_playlist. Read-only, costs no quota.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "search_id": "<search_id>",
      "title": "<title>"
    },
    "name": "preview_playlist"
  }
}

Input Schema

Name	Required	Description	Default
`title`	Yes	Playlist title (YouTube limit 150 chars).
`privacy`	No		unlisted
`sort_by`	No		score
`search_id`	Yes
`max_videos`	No
`description`	No	Playlist description.
`like_weight`	No
`custom_order`	No	Explicit final order (e.g. beginner → advanced). Listed videos come first in this order; the rest follow by sort_by.
`comment_weight`	No
`recency_weight`	No	0 = ignore upload date (default). 0.2–0.4 favours newer videos. Use when the user wants up-to-date content.
`max_per_channel`	No
`exclude_video_ids`	No	Off-topic or user-rejected videos (sticky).
`popularity_weight`	No
`restore_video_ids`	No	Undo earlier exclusions.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Adds context the annotations don't carry: exclusions persist across calls for the same search_id (a stateful side effect), the return value is markdown meant for human review, and the call costs no quota. 'Read-only' duplicates readOnlyHint=true, but the quota and stickiness disclosures are genuine additions.

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?

Three short sentences, front-loaded with the core action, then statefulness, then the required next step. No filler and no repetition of schema details.

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 14-parameter, output-schema-less tool it covers the essentials: what comes back (markdown), what to do with it, and why it's safe to call repeatedly. It falls short on guiding which of the many weighting/ordering parameters to set and when to rebuild versus start a new search.

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?

Schema coverage is only 43% across 14 params, and the description never explains the tuning knobs (weights, max_per_channel, sort_by, privacy). It does add the single most important semantic — that search_id carries remembered exclusions across calls — which lifts it above a pure-schema restatement, but it leaves too many parameters undocumented.

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 ('build or rebuild'), a specific resource ('a numbered playlist preview'), and its source ('from a search'), which distinguishes it from create_playlist and from the search_videos sibling in the same sentence group.

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?

Explicitly sequences the workflow: show the returned markdown, ask the user for approval or changes, then call create_playlist. It also names create_playlist as the alternative/downstream step, so an agent cannot confuse preview with the actual creation call.

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

Deploy Server