Postemi: Social Media Scheduler

create_upload_link

Upload a video or photo from the user's computer or phone to post it on social media (Facebook, Instagram, TikTok, YouTube, X). Shows an upload card in the chat, plus a link that also works on a phone, where the user drops the files in full quality: images up to 10 MB, videos up to 1 GB, mp4 or mov (a .mov becomes an .mp4 in the browser).

Use it when the file is on the user's device and not in the chat, for a video, when upload_media_from_url answers with lowResolution, or when a file transfer failed. A file attached in ChatGPT goes through upload_media_from_url first; after a successful upload, use its path and do not ask for the file again.

The flow:

Call this. Also give the returned url in your reply for clients without the card, and say: "Drop the photo or video on the card, or open this link, then tell me it is done."
When the user presses "Use in a post" on the card, you get the file paths in a message. Otherwise, when they say it is done, call list_upload_link_files with this uploadLinkId.
Pass the path as the create_post attachment.

The link works signed out for 120 minutes and takes several files. Call it once per batch; if it expires, call it again.

Magyarul: kép vagy videó feltöltése a gépről vagy telefonról, például Facebookra, Instagramra, TikTokra, YouTube-ra.

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": "create_upload_link"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description	Default
`error`	No
`output`	No

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?

Goes well beyond the annotations: 120-minute signed-out link lifetime, multi-file batches, call-once-per-batch guidance, re-call on expiry, size/format limits (10 MB images, 1 GB video, mp4/mov, .mov converted to .mp4), and what the user sees (an upload card). This directly clarifies the non-idempotent, non-read-only profile the annotations only hint at.

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 purpose sentence, then conditions, then a numbered flow — very scannable. The trailing Hungarian translation is unnecessary padding for an agent-facing tool, though it does not obscure the main content.

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?

Output schema exists, yet the description still supplies the critical operational context: what the returned URL is for, how the paths come back (card message vs. list_upload_link_files), and where the path goes next (create_post attachment). An agent can complete the whole workflow from this text alone.

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?

Zero parameters, so there is no schema semantics to explain; the description appropriately spends its words on the flow instead. It could briefly state that the call needs no arguments, but nothing is missing that would cause a mis-call.

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 (upload a video or photo to post on social media) and enumerates targets. It cleanly separates itself from siblings by noting that files already in the chat go through upload_media_from_url instead.

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?

Explicit when-to-use triggers: file is on the user's device, it is a video, upload_media_from_url returned lowResolution, or a transfer failed. It also gives the negative case (attached in ChatGPT → use upload_media_from_url, don't re-ask) and names the follow-up sibling list_upload_link_files.

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.