BlackOps Center

Upload Media

upload_media

Upload media to the site media library. Three modes:

URL mode — pass file_url + filename + content_type. Fetches server-side, one call, no human step. file_url must be https, SSRF-guarded (blocks private/loopback/link-local/metadata, re-checked on every redirect), capped at 50 MB (images/PDF) or 200 MB (video, under the 1 GB bucket limit to fit the 30s fetch timeout — bigger video needs the direct-PUT path below). Good when an agent already has a URL, e.g. from a generation call.
Interactive mode — pass nothing (or just domain/label). Returns { url, token, expires_at }: show the URL, the user signs in and uploads via the quick-upload page, then clicks "Done". Use for screenshots, recordings, or local files — avoids round-tripping bytes, supports bulk. filename/alt_text/title apply to the FIRST asset only (later images auto-generate their own; videos get none).
Claim mode — pass token (from interactive mode). Returns status="completed" with an assets[] array once the user clicks Done, or "pending" while they are still uploading — poll again.

No public URL but your own HTTP client? get_media_upload_url({ domain, filename, content_type }) → { asset_id, upload_url }, PUT your bytes, then finalize_media_upload({ asset_id, domain }) — token only, no browser. Example: content/docs/features/image-upload.mdx.

Supported: jpeg, png, webp, gif, mp4, webm, quicktime, application/pdf (quick-upload: video to 1 GB, else 50 MB). Video → media_type "video", no thumbnail. PDF → "document" (thumbnail = page one, 50 MB cap), asset_id + public URL like an image — the only document type; anything else rejected.

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"
  }
}

Input Schema

Name	Required	Description	Default
`kind`	No
`label`	No
`title`	No
`token`	No
`domain`	No
`ttl_ms`	No
`alt_text`	No
`file_url`	No
`filename`	No
`size_bytes`	No
`content_type`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With only destructiveHint=false supplied, the description carries the burden well: it discloses SSRF guards (private/loopback/link-local/metadata blocked, re-checked on redirects), size caps (50 MB images/PDF, 200 MB video URL fetch, 1 GB quick-upload), a 30s fetch timeout, and polling semantics for claim mode ('pending' vs 'completed'). Gaps remain: it never states what URL mode returns (asset_id/public URL is only implied for PDFs) and never explains kind, ttl_ms, or size_bytes, which are behavioral knobs (token lifetime in particular) an agent would want to know about.

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?

Numbered modes with bold-style lead-ins and a front-loaded one-line summary make it scannable despite its length, and the length is justified by three distinct call shapes. The closing 'Supported:' paragraph is dense but earns its place with format-to-media_type mappings; a little parenthetical hedging ('under the 1 GB bucket limit to fit the 30s fetch timeout') could be trimmed.

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?

For an 11-parameter, zero-required, no-output-schema tool with three modes, the description covers mode selection, constraint limits, return payloads for two of three modes, and format support. It is not fully complete because the URL-mode success response is unstated and ttl_ms/size_bytes/kind remain undocumented anywhere in the definition.

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 0% and required is empty, so the schema alone gives an agent nothing about which params to combine. The description compensates strongly by defining per-mode param bundles (file_url + filename + content_type; token; optional domain/label) and the token's provenance from interactive mode. Three of eleven parameters — kind, ttl_ms, and size_bytes — are never mentioned, which keeps this below a 5.

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+resource ('Upload media to the site media library') and immediately decomposes it into three named modes (URL, interactive, claim). It also distinguishes itself from the sibling tools get_media_upload_url and finalize_media_upload by naming them as the alternative path for callers with their own HTTP client.

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?

Each mode carries an explicit selection condition: URL mode 'when an agent already has a URL, e.g. from a generation call'; interactive mode 'for screenshots, recordings, or local files'; claim mode after interactive. It goes further and points to the two-sibling escape hatch (get_media_upload_url → PUT → finalize_media_upload) for the no-public-URL case, which is exactly the routing an agent needs.

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

All BlackOps Center 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?