Skip to main content
Glama

Find clip-worthy moments in a Twitch stream

find_moments
Read-onlyIdempotent

Finds the moments a Twitch stream's chat exploded (chat speed vs its normal pace, 'clip it' requests, clips viewers already made), and returns timestamps, a suggested clip window, event type, 3-5 hook lines, and music-claim risk (Twitch muted that audio for licensed music). Pass a Twitch or Kick channel (uses the live stream if live, else the latest one; Kick as kick.com/) or a VOD link. A 7-hour stream takes about 15-40 seconds.

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": {
      "source": "<source>"
    },
    "name": "find_moments"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many moments (default 8)
sourceYesTwitch channel name or URL, a Kick channel URL (kick.com/<name>), or a VOD URL (twitch.tv/videos/… or kick.com/<name>/videos/…)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / source / description
      Previous value: -"Twitch channel name or URL, or a VOD URL/id (twitch.tv/videos/...)"New value: +"Twitch channel name or URL, a Kick channel URL (kick.com/<name>), or a VOD URL (twitch.tv/videos/… or kick.com/<name>/videos/…)"
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive, so the marginal value here is operational: the live-vs-latest fallback for channels, a concrete latency expectation ('7-hour stream takes about 15-40 seconds'), and the music-claim risk signal derived from Twitch muting licensed audio. That is exactly the kind of cost and interpretation context an agent needs before invoking a long-running analysis.

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

Conciseness5/5

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

Three sentences, front-loaded with the purpose, then the return contract, then accepted inputs and latency. Clause-dense but every clause carries distinct information; nothing is restated from the title.

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?

There is no output schema, and the description compensates by enumerating the returned fields including the suggested clip window and music-claim risk. Input formats, the live-vs-VOD resolution rule, and expected runtime are all covered, leaving no meaningful gap for a two-parameter analysis tool.

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 schema already carries parameter documentation and 3 is the floor. The description still adds semantic value by explaining that `source` resolution depends on live status rather than being a plain identifier, which affects result freshness in ways the schema does not convey.

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?

Uses a specific verb plus resource ('Finds the moments a Twitch stream's chat exploded') and immediately operationalizes it with three concrete detection signals (chat speed vs normal pace, 'clip it' requests, existing clips). It also enumerates the exact return payload, so an agent knows what it gets back without opening anything.

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?

Clear usage context: pass a Twitch or Kick channel (live stream preferred, latest otherwise) or a VOD link, with the Kick URL format spelled out. There are no explicit exclusions or named alternatives, though the sibling catalog contains nothing functionally overlapping, so the guidance is effectively complete.

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.