Skip to main content
Glama
Sign In
YouTube Studio MCP

YouTube Studio MCP

by nelsonrogers
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Audience retention

get_audience_retention
Read-onlyIdempotent

Retrieve a video's audience-retention curve with timestamped watch ratios, retention milestones, and steepest drop-off moments to identify where viewers leave.

Instructions

The audience-retention curve for one video, with timestamps, key retention milestones and the steepest drop-off moments. Defaults to the video's lifetime.

audience_watch_ratio = share of viewers still watching at that moment (can exceed 1 when people rewatch a part). relative_retention compares with similar-length YouTube videos (0-1; above 0.5 is better than average).

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": {
      "video_id": "<video_id>"
    },
    "name": "get_audience_retention"
  }
}

Input Schema

NameRequiredDescriptionDefault
periodNoNamed date range, Studio-style. Rolling ranges end at the latest complete day of data (analytics lag ~2-3 days; dates are US Pacific). Ignored when start_date is set.
pointsNoNumber of points in the returned curve (down-sampled from 100).
end_dateNoCustom range end, YYYY-MM-DD (inclusive). Defaults to the latest complete day.
video_idYesThe video to analyse (one ID).
start_dateNoCustom range start, YYYY-MM-DD. Overrides `period`.
audience_typeNoOnly organic views, or views from in-stream / in-feed ads.
subscribed_statusNoOnly subscribers or non-subscribers.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description goes beyond them by explaining metric semantics an agent cannot get from annotations: watch ratio can exceed 1 due to rewatching, and relative_retention is a 0-1 benchmark where >0.5 beats similar-length videos. It does not mention latency, rate limits, or failure modes, but the added interpretive context is substantive.

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 short blocks: the first front-loads what is returned, the second defines the two metrics. No filler or repetition, though the metric glossary arguably overlaps with what an output schema may already convey, which keeps it from a perfect score.

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?

With 7 parameters, an output schema, and full schema descriptions, the definition only needs to carry interpretive meaning, which it does via the lifetime default and the metric definitions. An agent could call this correctly from the definition alone; only comparative routing against siblings is missing.

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%, so the schema already documents all seven parameters, which sets the baseline at 3. The description adds one genuinely new fact — that the default window is the video's lifetime, clarifying the meaning of a null period — but says nothing about filtering parameters such as audience_type or subscribed_status.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource and output shape: 'audience-retention curve for one video, with timestamps, key retention milestones and the steepest drop-off moments.' That is concrete enough to distinguish it from aggregate tools like get_performance_summary or get_metrics_over_time, but it never names a sibling or an alternative explicitly.

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 only usage-oriented statement is that the range 'Defaults to the video's lifetime,' which tells an agent what happens if period/start_date/end_date are omitted. There is no guidance on when to pick this tool over the breakdown or metrics-over-time siblings, and no exclusions or prerequisites.

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