oriiion

Create Post From Video

create_post_from_video

Create posts from a video the user provides. Pass EXACTLY ONE of mediaId (from finalize_media_upload or import_media_from_url — preferred for files you uploaded) or videoUrl (a public link). The video becomes the post's media and AI writes captions based on the topic. Runs asynchronously — the user is notified when posts are ready. Posts are always saved as DRAFTS: nothing is published or scheduled. To go live, call schedule_post or publish_post once the user confirms. Output: { success, taskId, groupId, count, finalStatus: 'draft', videoUrl, posts: [{ id, status: 'generating', index }] } — poll get_task_status with taskId.

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": {
      "topic": "<topic>"
    },
    "name": "create_post_from_video"
  }
}

Input Schema

Name	Required	Description
`count`	No	Number of caption variants/posts to generate (default 1; only more when the user asks for more)
`topic`	Yes	What the video/post is about (required for the caption)
`mediaId`	No	mediaId of a video stored with finalize_media_upload or import_media_from_url. Omit when you pass videoUrl.
`videoUrl`	No	Public HTTP/HTTPS URL of the video. Omit when you pass mediaId.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 25, 2026

addedInput schema / properties / mediaId

Added value: +{
+  "description": "mediaId of a video stored with finalize_media_upload or import_media_from_url. Omit when you pass videoUrl.",
+  "maxLength": 40,
+  "type": "string"
+}

changedInput schema / properties / videoUrl / description

Previous value: -"Public HTTP/HTTPS URL of the video"New value: +"Public HTTP/HTTPS URL of the video. Omit when you pass mediaId."

changedInput schema / required

Previous value: -[
-  "videoUrl",
-  "topic"
-]New value: +[
+  "topic"
+]

First observedOct 21, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say it is a non-destructive, non-idempotent write; the description adds the genuinely non-obvious traits: asynchronous execution, user notification, captions written by AI from the topic, and the critical constraint that posts are ALWAYS drafts with nothing published or scheduled. It also discloses the return shape and the polling tool, which annotations cannot convey.

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 action and the source-selection rule, then constraints, then output. The inline output JSON blob is verbose, but with no output schema it earns its place by telling the agent what to expect and what to poll.

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 an async, non-idempotent mutation with no output schema, the description covers everything material: required inputs, async semantics, draft-only side effect, the returned fields, and the follow-up tool. Nothing an agent needs to invoke it safely is missing.

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; the description earns above that by adding the mutual-exclusivity constraint and a preference ordering between mediaId and videoUrl that the schema only states as 'omit when you pass'. It does not add meaning for `topic` or `count`, which the schema already explains.

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+resource ('Create posts from a video') and immediately scopes it against siblings by naming create_post_from_image's domain analog and the media-producing tools (finalize_media_upload, import_media_from_url). An agent can distinguish it from create_from_link or generate_posts without opening any schema.

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?

Gives an explicit either/or rule ('Pass EXACTLY ONE of mediaId ... or videoUrl'), states the preferred option and why, and routes the follow-up action ('To go live, call schedule_post or publish_post once the user confirms'). That is when-to-use plus named alternatives plus the downstream step.

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

All oriiion 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?