Skip to main content
Glama
Fetchproof MCP Server

Fetchproof MCP Server

youtube_channel_search

Search a specific YouTube channel by keyword to find videos, Shorts, live streams, and playlists. Use the channel handle and optional continuation token to page through results.

Instructions

youtube: Channel Search. GET /v1/youtube/channel/search. Provide one of: handle, continuationToken. Search within one YouTube channel by keyword. Returns videos, Shorts, live streams and playlists. Costs 1 credit per page, even with no matches. Costs 1 credit when it succeeds. Errors, blocked or timed-out requests, invalid requests and cache hits cost nothing. A not-found or empty result is charged only where that operation's published cost says so.

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": {
      "handle": "<handle>",
      "query": "<query>"
    },
    "name": "youtube_channel_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesKeywords to search within this channel.
handleYesYouTube channel handle, with or without @.
continuationTokenNoToken from the previous response. Keep the same handle and query; stop when the token is null.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden, and it delivers a detailed cost model: one credit per page even with zero matches, one credit on success, and no charge for errors, blocked, timed-out, invalid, or cache-hit requests. That is exactly the kind of billing/auth-adjacent behavior an agent needs before calling. It does not mention rate limits or permission/auth requirements, 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 sentence is front-loaded and efficient, but the cost block is repetitive ('Costs 1 credit per page, even with no matches. Costs 1 credit when it succeeds.') and ends with a vague sentence about published costs that partly walks back the earlier 'even with no matches' claim.

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?

No output schema exists, so the description should convey return values, and it does by naming videos, Shorts, live streams and playlists, plus the continuationToken paginating model and the cost exposure. What is missing is the response shape or result ordering, and any note on permissions, for a 3-parameter channel-scoped search.

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 all three parameters are already documented, giving a baseline of 3. The description adds paginating intent but also introduces a conflicting claim ('Provide one of: handle, continuationToken') that omits the required query and contradicts the required-fields list.

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?

It gives a concrete verb and resource ('Search within one YouTube channel by keyword') and even lists the returned content types (videos, Shorts, live streams, playlists), so an agent can tell it apart from a global search tool. It never names the sibling it differs from, though, so differentiation is inferred from the scoping phrase rather than stated.

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?

Paginating guidance is explicit ('keep the same handle and query; stop when the token is null'), which is genuinely useful. There is no explicit statement of when to pick this over youtube_search or the per-tab tools (youtube_channel_videos etc.), and the opening line 'Provide one of: handle, continuationToken' is misleading against a schema that requires both handle and query.

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