Skip to main content
Glama

Eurekuh

Add media from a URL

upload_media

Download a publicly reachable image or video into the user's media library and return a mediaId for create_post. The file is fetched by the server from the URL you give — you do not send bytes. Accepts jpeg, png, webp, mp4, mov and webm; images up to 10MB (less on X, Instagram, Threads, Facebook, Bluesky and Google Business: check_limits measures it), video up to 1GB. Adding to the library publishes nothing.

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": {
      "url": "<url>"
    },
    "name": "upload_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesA public https URL to the image or video.
organizationIdNoWhich organization to act in: an id from list_organizations. Leave out for this connection's default organization.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description explains the fetching model (server-side download, no bytes sent), enumerates accepted formats, gives concrete size caps including the lower per-platform caps on X/Instagram/Threads/Facebook/Bluesky/Google Business, and reassures that 'Adding to the library publishes nothing' — the key non-destructive-but-not-read-only nuance.

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?

Four tight sentences ordered by importance: what it does, how it works, constraints, and side-effect scope. No filler, and the most decision-relevant facts (mediaId, no bytes, no publishing) are front-loaded.

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?

No output schema exists, and the description compensates by naming the mediaId return value. It covers formats, size limits, and side effects, but does not say what happens on a non-direct URL or an oversized file (error vs. truncation), which is the main remaining risk for a two-parameter ingestion tool.

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, and the description earns one more by clarifying that the URL is fetched server-side and must be publicly reachable, which is the actual failure mode an agent needs to avoid. It does not add anything about organizationId, though the schema already documents it fully.

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 gives a specific verb and resource ('Download a publicly reachable image or video into the user's media library') plus the output ('return a mediaId'). The clause 'you do not send bytes' implicitly separates it from upload_file, so an agent can pick between the two URL-based and byte-based paths.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the downstream use case explicitly ('return a mediaId for create_post') and routes size questions to check_limits, which is a concrete alternative-tool reference. It stops short of an explicit 'use this instead of upload_file when...' rule, so the contrast with the sibling is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources