Skip to main content
Glama

Start a video upload

create_upload

Step 1 of uploading a local video, up to 95 MB. Returns put_url: PUT the file bytes there yourself with the given headers (e.g. curl -T file.mp4 -H 'Content-Type: video/mp4' '<put_url>') within 10 minutes, then call commit_upload. purpose 'swap' = a reel to swap a character into; 'own' = your own video to post (Sharing).

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": {
      "purpose": "<purpose>",
      "content_type": "<content_type>",
      "size": "<size>"
    },
    "name": "create_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
sizeYesExact file size in bytes
purposeYes
filenameNo
content_typeYes

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?

Goes well beyond annotations by disclosing the 95 MB cap, a 10-minute upload window, that the client must perform the byte transfer itself with specific headers (with a concrete curl example), and that a separate commit step is required. These are exactly the non-obvious behaviors an agent would otherwise get wrong.

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 essential constraint and sequenced in execution order (create → PUT → commit), so the agent reads it correctly on one pass. The inline curl example is dense but earns its place by pinning down the required headers; a sentence could be tightened without losing meaning.

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?

There is no output schema, and the description compensates by documenting the returned put_url and how to use it. Combined with the size cap, timeout, and next-step pointer, an agent has everything needed to invoke it correctly.

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 description coverage is only 25%, so the description has to carry weight — and it does for the most ambiguous field by defining purpose 'swap' vs 'own', and for size by stating the real 95 MB limit that the schema's numeric maximum does not convey. It adds nothing for filename and only implies content_type via the curl header example, leaving a small gap.

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 ('Start a video upload', 'Step 1 of uploading a local video'), plus a hard size bound (95 MB). The 'Step 1' framing plus the explicit 'then call commit_upload' cleanly separates it from its closest sibling.

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?

Gives clear flow guidance: create the upload, PUT the bytes to put_url within 10 minutes, then call commit_upload. It also explains which purpose value to pick for each scenario. It stops short of stating exclusions (e.g., that remote/URL sources should go through a different tool), so it is not a full when/when-not treatment.

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.