Skip to main content
Glama

check_discoverability

Read-only

Diagnose how the signed-in user's own YouTube channel gets FOUND, and whether new people are finding it at all. Returns whether their views come from people who already subscribe or from new viewers discovering them, through which door people arrive (search, suggested, browse, external), and the actual searches already bringing them viewers, with the one thing to change to get discovered more. Call this for reach and discovery, however phrased: why am I not getting discovered or found, how do I get found or rank in search, why isn't the algorithm pushing / recommending / suggesting my videos, how do I reach new people or grow beyond my current subscribers, am I only reaching people who already follow me, what searches or keywords bring people to my videos, how do people find me, where does my traffic come from, how do I get more reach or discovery. Pass video (a title or part of one) to zoom into ONE upload and diagnose whether THAT video's problem is reach (few people find it) or conversion (people find it but do not subscribe), through which door it is found, and the searches that found it: use this when the user asks why a SPECIFIC video is not getting found, discovered, recommended, or reaching new people, or whether a video's problem is reach or getting subscribers. Always the user's own channel. For WHO the audience is (age, gender, location), use analyze_audience; for a single video's overall performance, why it flopped, or where viewers dropped off, use analyze_video; for the ranked list of videos to fix, use diagnose_channel. Needs no input: it reads their real connected YouTube channel directly. Never ask the creator anything first, not for context, not for a link, not for a title you could look up; call it immediately.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "check_discoverability"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNo
videoNoOptional: a specific upload to diagnose the reach-vs-conversion of, given as its title or part of it, or 'latest' for the most recent upload. Omit entirely for the whole channel

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish readOnlyHint and openWorldHint, so safety is covered. The description adds real operational context beyond that: it reads the user's real connected channel directly, requires no input, and explicitly forbids asking the creator for context or links first — which prevents a common failure mode of pre-call clarification. It does not discuss latency, quota, or what happens if no channel is connected, which keeps it from a 5.

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

Conciseness3/5

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

The purpose and the `video` mode are front-loaded, which is good. But the paraphrase list is bloated and repetitive ('discovered / found', 'recommended / suggesting', 'reach or discovery' recur across sentences and the final paragraph restates the alternative-tool routing already given earlier). The closing 'never ask the creator anything' sentence repeats the same instruction three ways.

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 no output schema, the description carries the return-value burden and does so thoroughly, and it covers the no-required-input, own-channel-only contract. For a zero-required-parameter read tool with rich annotations, that is nearly complete; the one hole is the unexplained `title` parameter.

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 50%: `video` is documented in the schema and the description usefully extends it with 'part of one' and the 'latest' sentinel plus a clear omit-for-whole-channel semantic. However, the `title` parameter is never mentioned anywhere — not in the schema, not in the description — leaving one of two parameters with no meaning at all. The description partially compensates but leaves a genuine blank.

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 opening sentence gives a specific verb and resource: 'Diagnose how the signed-in user's own YouTube channel gets FOUND, and whether new people are finding it.' It then enumerates the returned dimensions (subscriber vs. new-viewer split, traffic door, actual search queries, one recommended change), so the agent knows exactly what class of answer this produces. It is clearly distinct from analyze_audience (who) and analyze_video (single-video performance).

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?

Usage is spelled out at both levels: a long list of user phrasings that should route here ('why am I not getting discovered', 'where does my traffic come from'), plus the specific condition for the `video` mode ('a SPECIFIC video is not getting found'). It also names three sibling alternatives and the conditions that select them (analyze_audience for demographics, analyze_video for flops/drop-off, diagnose_channel for a ranked fix list).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources