OpenClip

Submit Video Tool

submit_video

Submit a source video url (YouTube, Vimeo, Google Drive, Dropbox, OneDrive, Rumble, or a direct video file) to turn into viral clips, with an optional title. Returns the new video id (a hashid) and its status.

Processing is ASYNCHRONOUS: this returns status: "downloading" or a paused pending_credits state. Poll get_video_status with the returned id while processing moves. Do not poll pending_credits: when a failed payment caused the pause, the result includes payment_required: true, a message, and billing_url; show that guidance so the user can repair payment.

Optionally pass an agent id (a hashid from list_agents) to process the video with that agent's settings (caption preset, composition defaults, …); omit it to use the team's defaults.

Safe to retry: submitting the same url + agent again returns an existing run for it from the last 24h (still processing, or completed) as deduped: true instead of starting a second run. Submitting the same url with a DIFFERENT agent starts a new run (so you can re-process a source with another agent). A previously failed url can be resubmitted to retry it.

Errors: an unsupported/invalid URL is rejected and an agent not on your team is rejected. A missing subscription or insufficient credits parks the video in pending_credits; direct the user to OpenClip before checking again.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	The source video URL to process (a supported provider or a direct video file).
`agent`	No	Optional agent id (hashid from list_agents) whose settings control processing/rendering. Must be one of your team's agents. Omit to use team defaults.
`title`	No	Optional title for the video; defaults to the source title.

Output Schema

TableJSON Schema

Name	Required	Description
`video`	Yes	The video id (hashid). Pass it as `video` to get_video_status, list_clips, get_render_status and render_clip.
`status`	Yes	The video status. downloading, uploaded and processing are in-flight; pending_credits is paused; completed, failed and download_failed are terminal.
`deduped`	Yes	True when an existing run for this url + agent from the last 24h was returned instead of starting a new one.
`message`	No	User-safe billing recovery guidance. Present with payment_required or subscription_required.
`billing_url`	No	OpenClip billing page where the user can recover. Present with payment_required or subscription_required.
`payment_required`	No	Present and true when an open failed subscription payment is blocking processing.
`subscription_required`	No	Present and true when terminal payment failure requires a new subscription.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "billing_url": {
+      "description": "OpenClip billing page where the user can recover. Present with payment_required or subscription_required.",
+      "type": "string"
+    },
+    "deduped": {
+      "description": "True when an existing run for this url + agent from the last 24h was returned instead of starting a new one.",
+      "type": "boolean"
+    },
+    "message": {
+      "description": "User-safe billing recovery guidance. Present with payment_required or subscription_required.",
+      "type": "string"
+    },
+    "payment_required": {
+      "description": "Present and true when an open failed subscription payment is blocking processing.",
+      "type": "boolean"
+    },
+    "status": {
+      "description": "The video status. downloading, uploaded and processing are in-flight; pending_credits is paused; completed, failed and download_failed are terminal.",
+      "enum": [
+        "downloading",
+        "download_failed",
+        "uploaded",
+        "pending_credits",
+        "processing",
+        "completed",
+        "failed"
+      ],
+      "type": "string"
+    },
+    "subscription_required": {
+      "description": "Present and true when terminal payment failure requires a new subscription.",
+      "type": "boolean"
+    },
+    "video": {
+      "description": "The video id (hashid). Pass it as `video` to get_video_status, list_clips, get_render_status and render_clip.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "video",
+    "status",
+    "deduped"
+  ],
+  "type": "object"
+}

First observedJul 7, 2026

TDQS

A5/5.0

Behavior5/5

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

Rich behavioral disclosure: async processing returns status immediately, parking in pending_credits, payment failure details, dedup behavior, failed-url retry semantics, and unsupported-agent/URL rejection. Even though annotations are empty, the description fully discloses what happens in each outcome path.

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?

The description is long but earned: every paragraph covers a distinct concern (purpose, async behavior, dedup, errors). Key claims are front-loaded in the first sentenceaiman. It uses consistently formatted inline code (url), makes repetitive semantics (deduplicated, pending_credits) coherent, and avoids redundancy across paragraphs.

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?

Given the tool has an output schema, the description need not list return fields, but it still covers the critical runtime concerns: poll destination, payment-repair path, retry behavior, and agent validation. An agent has everything needed to invoke it correctly with zero additional lookups.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions, and the tool description goes beyond: it explains that `agent` controls processing/rendering defaults and is checked for team membership, that `url` must be from supported providers (exhaustive list), and that `title` defaults to source title. This adds operational meaning beyond schema type/required flags.

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?

The description opens with a specific verb and resource ('Submit a source video URL') and states the core action: turn the source into viral clips, with acceptable providers enumerated. It also mentions the returned id/status which is the key artifact of submission. This clearly differentiates from siblings that edit, generate, or convert media.

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 sibling tools (edit_video, generate_ugc, remove_background, convert_media) as alternatives for other video tasks, telling the agent when NOT to use this tool. It also provides clear guidance on polling get_video_status and not polling pending_credits, as well as dedup/retry semantics. No ambiguity remains about when to invoke this tool.

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

All OpenClip 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?