Skip to main content
Glama
Sign In
YouTube Channel MCP

YouTube Channel MCP

by joinhackyard
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Choose AI models

set_ai_models
Idempotent

Assign a specific provider and model to each job, such as text, image, vision or transcription, by passing "provider:model" values, or pass null to restore the automatic model choice.

Instructions

Pick which connected provider and model handle each job, as "provider:model" (Azure: "azure:"), e.g. text "anthropic:claude-opus-5-5", image "openai:gpt-image-2", transcribe "groq:whisper-large-v3". Pass null to go back to the automatic choice.

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": "set_ai_models"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNo
imageNo
effortNoReasoning effort for Claude (default medium).
visionNo
transcribeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare non-readOnly, idempotent, non-destructive, and closed-world, so the mutation profile is largely covered. The description adds the null-resets-to-auto behavior and the "connected provider" prerequisite, but leaves the important question open: whether passing only one slot leaves the other slots untouched or resets them.

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?

One compact sentence front-loads the action and format before the examples, and no words are wasted. The nested quoting in the examples makes it slightly denser to parse than necessary, but nothing is extraneous.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no output schema and thin per-parameter documentation, the description covers format and reset semantics but omits error behavior for an unknown or unconnected model, and whether an invalid string is rejected or silently stored.

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?

With only 20% schema coverage, the description carries most of the semantic load, and it does well: it defines the "provider:model" string format, the Azure "azure:<deployment>" exception, worked examples for text/image/transcribe, and the null reset. The gap is the vision slot, which gets no example or explanation anywhere.

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?

"Pick which connected provider and model handle each job" gives a specific verb plus resource, and the per-slot examples (text, image, transcribe) make the concept concrete. It never references the nearest sibling, ai_status, so an agent must infer that this sets preferences while ai_status only reports them.

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?

"Pass null to go back to the automatic choice" is real usage guidance for resetting a slot, but there is no guidance on when to call this versus checking ai_status first, or whether the named provider must already be connected.

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