Skip to main content
Glama
Sign In

StreamClipping AI

by ai.streamclipping
OverviewDiscussionsAdmin

Import a VOD

import_vod

Creates a project from a Twitch, YouTube, Kick or CHZZK VOD (stream replay) link. Importing does not start clipping: start_clipping is the next step once the project reaches AWAITING_CROP.

Input Schema

NameRequiredDescriptionDefault
urlYesLink of the VOD to import. Twitch (twitch.tv), YouTube (youtube.com, youtu.be), Kick (kick.com) or CHZZK (chzzk.naver.com/video/…). The stream must be over and the replay public.
titleNoProject title. Defaults to a title derived from the date. Ignored for YouTube links: the project starts with a neutral title and gets the video's own title when it is downloaded.
creatorNoAgency creator to scope to, by name or id (see the creator profiles of the account). 'default' targets the default profile, the one without a named creator. Omit to cover all creators of the organization.
languageNoSpoken language as a 2-letter ISO code (fr, en, es…). Omit to let automatic detection decide.

Output Schema

NameRequiredDescriptionDefault
hintYes
statusYes
projectIdYes
nextActionYes
waitSecondsYes
alreadyImportingYesTrue if this source was already being imported: no duplicate was created.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / title / description
      Previous value: -"Project title. Defaults to a title derived from the date."New value: +"Project title. Defaults to a title derived from the date. Ignored for YouTube links: the project starts with a neutral title and gets the video's own title when it is downloaded."
  2. Changed1 schema field changed
    • addedInput schema / properties / creator
      Added value: +{
+  "description": "Agency creator to scope to, by name or id (see the creator profiles of the account). 'default' targets the default profile, the one without a named creator. Omit to cover all creators of the organization.",
+  "maxLength": 100,
+  "minLength": 1,
+  "type": "string"
+}
  3. First observed

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare mutation (readOnlyHint=false) and non-idempotency, and the description adds pipeline-state context (project lands in AWAITING_CROP, clipping not started). It does not cover duplicate imports of the same URL, failure behavior for private/ended streams beyond what the schema says, or auth needs — the remaining gaps are meaningful for a non-idempotent create.

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?

Two sentences, zero filler. Purpose first, then the state/next-step constraint, which is the highest-value thing an agent needs to know before calling.

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?

Output schema exists, so return values need not be explained, and the description covers purpose plus the state transition that gates the next tool. It stops short of noting invalid/private-VOD failure modes or duplicate-import consequences, a small but real gap for a create operation.

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 description coverage is 100%, so per-parameter meaning is fully documented in the schema (platform URL forms, title fallback for YouTube, creator scoping, ISO language). The description adds nothing parameter-specific, but it reinforces the accepted platform set at URL level, which is slightly beyond the schema baseline.

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 a specific verb ('creates a project') and resource (a VOD from named platforms), and explicitly distinguishes the action from start_clipping, a listed sibling. An agent can tell exactly what this tool does and where it sits in the pipeline.

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?

Explicitly names the follow-up step: 'Importing does not start clipping: start_clipping is the next step once the project reaches AWAITING_CROP.' That gives the agent both the when-to-use condition and the routing to the sibling tool after the call succeeds.

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

All StreamClipping AI toolsInspect
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