Skip to main content
Glama
Sign In

ShortSync

by app.shortsync
OverviewDiscussionsAdmin

Finish upload

finalize_video_upload

Finalizes an upload started with create_video_upload. Call this after PUTting bytes to the presigned URL. Returns { status: 'ready', video_upload_id, filename, content_type, size_bytes } once the bytes are in S3, or { status: 'reserved' } if the PUT hasn't landed yet (retry in a few seconds). Errors: unsupported file type (only mp4/mov/webm/mkv/avi videos and jpeg/png/webp/gif/heic images are allowed) or file too large (video 950 MB, image 20 MB). The upload also finalizes on its own via a background timer within a few minutes of the PUT, so calling this is optional but faster.

Input Schema

NameRequiredDescriptionDefault
upload_idYesThe upload_id returned by create_video_upload (a video_settings row id).
workspace_idNoOptional. Workspace the upload belongs to; found from upload_id when left out. If given, it must match the workspace_id passed to create_video_upload.
idempotency_keyNoOptional client-generated key (e.g., a UUID) to make retries safe. Identical calls with the same key within 10 minutes return the original result instead of running the write twice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / workspace_id / description
      Previous value: -"Workspace the upload belongs to. Must match the workspace_id passed to create_video_upload."New value: +"Optional. Workspace the upload belongs to; found from upload_id when left out. If given, it must match the workspace_id passed to create_video_upload."
    • changedInput schema / required
      Previous value: -[
-  "upload_id",
-  "workspace_id"
-]New value: +[
+  "upload_id"
+]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond annotations by documenting both return states, the retry guidance for the 'reserved' case, allowed MIME types, size caps, and the background-timer auto-finalization. Annotations only cover readOnly=false and destructive=false; the description supplies the substantive behavior (mutation semantics, delay window, optionality).

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?

Front-loads the purpose and sequencing, then stacks return values, error conditions, and the optionality note in compact sentences. Every sentence carries distinct information with no repetition of the title or annotations.

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?

No output schema exists, yet the description inlines both response shapes ({status:'ready',...} and {status:'reserved'}) plus error cases and retry timing, leaving nothing an agent needs in order to invoke and interpret this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so upload_id, workspace_id, and idempotency_key are already fully documented. The description adds no parameter-level detail (e.g., it never mentions idempotency or workspace matching), so it sits at the baseline where schema does the work.

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 and ties it directly to its predecessor ('Finalizes an upload started with create_video_upload'), which disambiguates it from siblings like create_video_upload and cancel_scheduled_post. An agent can identify this as the terminal step of the upload lifecycle without opening the schema.

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?

Explicitly says when to call ('after PUTting bytes to the presigned URL') and offers the alternative path ('the upload also finalizes on its own via a background timer... calling this is optional but faster'). This is a clear when/when-not with a named alternative mechanism.

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

All ShortSync toolsInspect
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