Skip to main content
Glama

Upload a screen recording for UGC

autoshort_ugc_upload_recording

Upload an MP4/MOV screen recording for Silent UGC and receive a recordingAssetId to create a campaign. Supports public HTTPS URLs or base64 files within size limits.

Instructions

Upload the app screen recording for Silent UGC and get its recordingAssetId (for autoshort_ugc_create_campaign). Pass recordingUrl (a public https link — fetched by AutoShort, not by you; up to 50 MB) or recordingBase64 (at most 10 MB; larger files must use recordingUrl). MP4 or MOV, 3-60 seconds, at most 50 MB, checked from the file itself. The stdio package also accepts a local recordingPath. Free.

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": "autoshort_ugc_upload_recording"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNameNo
recordingUrlNoPublic https URL of the MP4/MOV (redirects are followed and re-checked).
recordingPathNoAbsolute path to a local MP4/MOV screen recording up to 10MB (read and uploaded by this local server). Larger files: pass recordingUrl.
recordingBase64NoThe MP4/MOV file, base64-encoded, at most 10 MB.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.3.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, but the description adds behavior those annotations cannot convey: the URL is fetched by AutoShort rather than by the agent, validation is performed against the file itself, and the call is free. It does not explain what happens if the same file is uploaded twice or how validation failures surface, which are the main remaining behavioral gaps for a non-idempotent write.

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?

The definition is dense and front-loaded, leading with purpose and the returned asset id before transport details. It does repeat the constraints ('MP4 or MOV', '50 MB') twice within the same paragraph, which is avoidable redundancy.

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?

With no output schema, the description correctly supplies the return value (recordingAssetId) and enough acceptance criteria (format, duration, size, validation source) to call the tool confidently. It is not fully complete: the purpose of the 'fileName' parameter and the behavior for duplicate or failed uploads are not covered.

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 75%, so the baseline is 3, but the description adds genuine meaning: it explains the server-side fetch semantics of recordingUrl ('fetched by AutoShort, not by you') and the size-driven choice between URL and base64, which the schema only implies. It adds nothing about 'fileName', which remains undocumented in both the schema and the description.

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 and resource ('Upload the app screen recording for Silent UGC') and states the concrete outcome ('get its recordingAssetId'), then ties that output to the consuming tool 'autoshort_ugc_create_campaign'. An agent can distinguish this from sibling tools like autoshort_ugc_preview or autoshort_ugc_create_campaign without inspecting any schema.

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 gives clear routing rules between the three upload channels: use recordingUrl for files up to 50 MB, recordingBase64 for at most 10 MB, and recordingPath only in the stdio package. It does not state explicit exclusions (e.g., when to prefer an existing asset over re-uploading) or preconditions such as account/credit state beyond 'Free', so it stops short of a 5.

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