Postemi: Social Media Scheduler

upload_media_from_url

Upload an image or video for a social media post (Facebook, Instagram, TikTok, YouTube, X) into the user's Postemi media library; it comes back as a hosted { id, path } to attach to a post.

Accepts ONE of: a file attached or generated in this chat (preferred; pass it in the file field), a public https URL, or a complete data URL you already hold (data:image/png;base64,...).

Keep the original quality: never put a file into a base64 argument, resize, recompress or truncate it to make it fit; a truncated data URL is refused because the image is decoded before it is stored. Call this ONCE per image, pass the returned PATH (not the id) as the create_post attachment, and do not regenerate an image that uploaded. After a successful upload, do not ask the user for the same file again.

If the file transfer fails, or the answer has lowResolution, say so in one sentence and offer create_upload_link: an upload card where the user drops the original in full quality. Videos the chat cannot pass on go through create_upload_link directly.

Magyarul: kép vagy videó feltöltése posztoláshoz.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "upload_media_from_url"
  }
}

Input Schema

Name	Required	Description	Default
`url`	No	A public https URL, OR a data URL (data:image/png;base64,...) of an image you generated yourself.
`file`	No	The original image or video attached or generated in this ChatGPT conversation. Prefer this native transfer and preserve its original quality.

Output Schema

Name	Required	Description
`id`	No
`path`	No
`error`	No
`width`	No	Pixel width of a stored image.
`height`	No	Pixel height of a stored image.
`lowResolution`	No	Set when the image is small for a social post. Tell the user, and offer create_upload_link so they can upload the original file in full quality.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 29, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare the mutation/open-world profile, but the description adds real behavior: truncated data URLs are refused because the image is decoded before storage, quality is preserved, videos the chat cannot pass must go through create_upload_link, and a lowResolution response should be surfaced in one sentence. It also forbids re-asking the user for the same file, which is not derivable from any structured field.

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 purpose and return value, then source options, then quality rules, then failure routing — a sensible order. Slightly long, and the closing line 'do not ask the user for the same file again' partly restates the 'never re-upload a generated image' point, but most sentences carry distinct operational rules.

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?

An output schema exists, so return values need not be explained beyond the { id, path } pointer, and the description still supplies the decision-relevant extras: preferred source, quality preservation, video fallback, and the lowResolution branch. Nothing an agent needs to invoke this correctly 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 description's job is to add the constraint the schema omits — that only ONE of url/file is supplied, that file is preferred for native quality transfer, and that files must never be stuffed into a base64/URL argument. It stops short of describing mismatch or error behavior if both are passed, so it is strong rather than exhaustive.

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 and resource ('Upload an image or video ... into the user's Postemi media library'), names the target platforms, and describes the return shape ('a hosted { id, path } to attach to a post'). That is distinctly different from its siblings create_post and fotoai_generate.

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 enumerates the three accepted sources with a stated preference order ('file ... preferred', public https URL, data URL), and routes the failure/video cases to a named alternative: 'offer create_upload_link'. It also constrains call frequency ('Call this ONCE per image') and tells the agent which returned value to use downstream.

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

All Postemi: Social Media Scheduler 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.