Skip to main content
Glama

audit_channel

Read-only

Give the signed-in user a full audit and overview of THEIR OWN YouTube channel in one answer: the overall state right now, what is working and why, which single thing is constraining the channel (whether people are not being SHOWN the videos or are being shown and not clicking), and what their audience wants. This is the broad front-door command, and it reads the channel as a whole. For a ranked list of which VIDEOS to fix first and in what order, call diagnose_channel instead. Call it when the user asks to audit, analyze, review, assess, evaluate, or check their channel; wants a channel overview, health check, summary, or the big picture; or asks broad questions like 'how is my channel doing', 'what is going on with my channel', 'analyze my channel', or 'give me my channel overview'. ALWAYS pass ask: 'broad' when they asked to audit/review/analyze the channel or how it is doing overall, 'specific' when they asked for the channel read but aimed it at ONE thing (an audit focused on their titles, a review that only cares about packaging). Pass refresh: true ONLY when they explicitly want the numbers re-pulled rather than the last saved read (they say it is out of date, or they just published and want it counted); it is slower and Klyf Pro only. This is a SNAPSHOT of right now: for anything about direction over time (is it growing or sliding, why growth stalled, is this month better than last) call check_growth instead, or first, since a snapshot cannot see a trend and will contradict it. Always about the user's own connected channel, never a competitor's. 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": "audit_channel"
  }
}

Input Schema

NameRequiredDescriptionDefault
askNoHow wide the user's question is. 'broad' when they asked for an audit, an overview, or how the channel is doing overall. 'specific' when they asked for the whole-channel read but pointed it at ONE thing, for example 'audit my channel, focus on my titles' or 'review my channel, is my packaging the problem'. Do NOT reach for 'specific' on a narrow question that belongs to another tool: what to fix first is diagnose_channel, why growth stalled is check_growth, and reaching new people is check_discoverability. A broad ask opens by describing what the channel is and who it serves; a specific one answers only what was asked. Default is broad.
refreshNoRecompute from YouTube instead of reading the last saved analysis. Klyf Pro only; takes noticeably longer

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

A4.8/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, it discloses that the result is a point-in-time snapshot that cannot see trends and may contradict trend tools, that refresh is slower and gated to Klyf Pro, and that it reads the real connected channel with no user input required. These are exactly the operational traits an agent needs and that the annotations do not carry.

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?

The critical routing information is front-loaded and each paragraph has a job (what it does, alternative tools, when to call, parameter rules, snapshot caveat, no-input requirement). It runs long with ALL-CAPS emphasis and some redundancy, notably the repeated point that it reads the user's own connected channel and needs no input.

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 two-parameter, zero-required, read-only tool with no output schema, the definition covers purpose, sibling routing, parameter selection, freshness/latency/tier behavior, and scope boundaries. Nothing an agent needs in order to call it correctly is missing.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds decision rules the schema only partly encodes: 'ALWAYS pass ask: broad' for audit/review/overall questions versus 'specific' for a single-focus read, and 'refresh: true ONLY' when the user says numbers are stale or newly published. That routing guidance is meaningful, though it largely restates the enum documentation already in the schema.

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 opens with a specific verb and resource: 'Give the signed-in user a full audit and overview of THEIR OWN YouTube channel,' and enumerates what the answer contains (current state, what's working, the single constraint, audience wants). It explicitly distinguishes itself from siblings by naming diagnose_channel for ranked video fixes and check_growth for trends, so an agent can route without opening any schema.

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?

It gives an explicit trigger list ('audit, analyze, review, assess, evaluate, or check their channel'), concrete example phrasings, and clear exclusions pointing to diagnose_channel and check_growth. It also rules out competitor channels and states the tool should be called immediately without asking the user for input.

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