Skip to main content
Glama
Sign In
YouTube MCP

YouTube MCP

by pratikgh0se
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

youtube_approve

Destructive

Approve a pending YouTube preflight preview by approvalId with confirm: true, so you can review the exact operation, target, and change before calling the matching execute tool.

Instructions

Approve ANY pending preflight preview (upload, metadata, archive, thumbnail, caption, playlist, comment reply/moderation/delete, channel profile edit, bulk unsubscribe) by approvalId, with confirm: true. The result echoes the operation kind, target and exact desired change so the human can see precisely what is approved. Approval is single-use, expires, and is bound to the active profile and channel; then call the matching execute tool with confirm: true.

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": {
      "approvalId": "<approvalId>"
    },
    "name": "youtube_approve"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNoMust be true to approve; set it only after the user reviewed the preview.
approvalIdYesApproval ID returned by any youtube_preflight_* tool for the exact change.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.3.1
    • addedInput schema / properties / approvalId / description
      Added value: +"Approval ID returned by any youtube_preflight_* tool for the exact change."
    • addedInput schema / properties / confirm / description
      Added value: +"Must be true to approve; set it only after the user reviewed the preview."
  2. Addedv0.3.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations supply only destructiveHint=true; the description carries the real behavioral load: approval is single-use, expires, and is bound to the active profile and channel. It also discloses that the result echoes operation kind, target and exact desired change, which matters because there is no output schema.

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

Conciseness4/5

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

Two dense sentences, front-loaded with the action and scope. The long parenthetical list of operation kinds is bulky but earns its place by defining coverage; the sequencing instruction follows logically.

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?

Covers everything an agent needs: which tool to call this after, the required flag and human-review precondition, single-use/expiry/binding constraints, what the response contains, and which tool to call next. Missing output schema is compensated in prose.

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 100% and both parameters are already documented there, including the confirm-only-after-review caveat. The description's 'with confirm: true' and 'by approvalId' largely restate the schema, so the baseline 3 applies.

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 (Approve) and a precisely scoped resource (ANY pending preflight preview), then enumerates the operation families it covers — upload, metadata, archive, thumbnail, caption, playlist, comment moderation, channel edit, bulk unsubscribe. That enumeration makes it unambiguously distinct from the per-operation youtube_preflight_* and execute siblings.

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 gives the precondition (an approvalId returned by a preflight tool for the exact change), the required flag (confirm: true, set only after the human reviewed the preview), and the follow-up step (call the matching execute tool with confirm: true). No ambiguity about where this sits in the preflight→approve→execute sequence.

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

Deploy Server

Other Tools