LLMExpert: cited Q&A over YouTube videos

Add YouTube sources to a collection

add_sources

Charged like transcribe. Expand the given YouTube URLs, charge for the new work and start an ingest job in an existing collection. Maps to POST /v1/collections/{collectionId}/sources. $0.01/min standard, $0.03/min whisper by default, 1-minute minimum per video. Videos already in the collection are free. Pass a quote_id from quote to be charged exactly that price. Poll get_status every 10–30 s until status is completed, partial or failed; completed means every accepted video is transcribed and indexed, so the collection is queryable. API key required (the key's write scope). Prices are the service defaults; quote returns the exact price.

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": {
      "collection_id": "<collection_id>"
    },
    "name": "add_sources"
  }
}

Input Schema

Name	Required	Description
`url`	No	One YouTube URL (video, @handle, /channel/UC…, or playlist).
`urls`	No	Several YouTube URLs.
`quality`	No	Transcription quality (default standard).
`language`	No	Optional BCP-47 hint for transcription, e.g. en.
`quote_id`	No	A `quote_id` from `quote`: charges exactly the quoted price (400 if unknown or expired).
`channel_url`	No	`https://www.youtube.com/@handle`, `/channel/UC…`, or a playlist URL.
`channel_urls`	No	Several channel or playlist URLs.
`collection_id`	Yes	Collection to add the sources to.
`exclude_shorts`	No	Skip videos of 3 minutes or less when expanding a channel or playlist (default true); explicit video URLs are never skipped.
`idempotency_key`	No	Idempotency-Key for safe retries.
`min_duration_seconds`	No	Skip expanded videos shorter than this many seconds.
`max_videos_per_channel`	No	Newest-first cap on eligible videos per channel or playlist (default 25); Shorts and videos below min_duration_seconds are skipped before the cap.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 21, 2026

addedInput schema / properties / exclude_shorts

Added value: +{
+  "description": "Skip videos of 3 minutes or less when expanding a channel or playlist (default true); explicit video URLs are never skipped.",
+  "type": "boolean"
+}

changedInput schema / properties / max_videos_per_channel / description

Previous value: -"Newest-first cap applied to each channel or playlist (default 25)."New value: +"Newest-first cap on eligible videos per channel or playlist (default 25); Shorts and videos below min_duration_seconds are skipped before the cap."

addedInput schema / properties / min_duration_seconds

Added value: +{
+  "description": "Skip expanded videos shorter than this many seconds.",
+  "maximum": 14400,
+  "minimum": 0,
+  "type": "integer"
+}

First observedOct 19, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only say readOnlyHint=false and openWorldHint=true; the description adds substantial non-obvious behavior: per-minute pricing with a 1-minute minimum, videos already in the collection are free, quote_id freezes the price (400 if unknown/expired), and write-scope API key requirement. This is exactly the context annotations cannot 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?

Front-loaded with the charge-and-ingest action, then endpoint, pricing, workflow, and auth. Dense and mostly waste-free, though the quote-exactness point is stated twice ('Pass a quote_id...' and 'Prices are the service defaults; quote returns the exact price'), which is mild redundancy.

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 12-parameter mutating tool with no output schema, the description covers cost model, idempotency expectations, the polling contract for observing completion, and auth scope — enough for an agent to invoke and follow up correctly.

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 pricing meaning tied to the `quality` parameter ($0.01/min standard vs $0.03/min whisper) and clarifies quote_id's exactness guarantee, going beyond the schema's field-level notes.

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?

States specific verbs and resource: 'Expand the given YouTube URLs, charge for the new work and start an ingest job in an existing collection', plus the exact endpoint POST /v1/collections/{collectionId}/sources. The plural contrast with the sibling add_source is implicit in 'URLs'/'existing collection' and reinforced by the batch-oriented param set.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete workflow guidance: pass a quote_id from quote to lock price, poll get_status every 10-30s until completed/partial/failed, and the auth scope required. It does not explicitly say when to prefer add_sources over the singular add_source sibling, which is the main gap.

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

All LLMExpert: cited Q&A over YouTube videos tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?