Skip to main content
Glama
Sign In

ShortSync

by app.shortsync
OverviewDiscussionsAdmin

List importable content

list_import_items
Read-only

Browses content the user can import from tools they connected in ShortSync (Settings > Integrations). Without source: lists the sources available to the user and whether each is connected. If one isn't, tell the user to connect it there. With source: lists its items (id, title, caption an import gets, duration_ms, created_at, plus source-specific fields). Sources with projects (has_containers) first return containers; pass one's id as container_id to list its items. Pass next_cursor back as cursor for more. Sources:

  • canva: The user's Canva designs, newest first; query searches titles. PNG imports one image per page (in order, ready for create_carousel); MP4 imports one video. The design title is the caption. Options: format (import): png|mp4, default png. png: one image per page. mp4: one video.

  • opusclip: Clips OpusClip cut from the user's long videos, with OpusClip's caption and hashtags. Projects first. Import takes 15-90 s while OpusClip renders.

  • klap: Clips Klap cut from the user's long videos, best first, with a caption Klap's AI writes at import. Projects first. Each import uses one export from the user's Klap plan and takes 20 s to 2.5 min.

  • twitch: Clips from the user's own Twitch channel, most viewed first. The clip title is the caption. Options: range (list): 7d|30d|365d|all, default all. Only clips made in the last 7d, 30d or 365d. format (import): portrait|landscape, default portrait. portrait falls back to landscape when Twitch has no portrait version.

  • heygen: Videos in the user's HeyGen account, newest first. Only status completed imports. The video title is the caption. Options: version (import): original|captioned, default original. captioned is HeyGen's version with burned-in captions, when it has one.

  • descript: Compositions in the user's Descript Drive (the one their token belongs to), imported as 1080p MP4. Projects first, most recently edited first. The composition name is the caption. Import takes up to 2.5 min while Descript renders; audio-only compositions can't be imported.

  • onedrive: Videos and images in the user's OneDrive. Pass a folder id as container_id to list inside it (root when omitted); items with type "folder" are subfolders, only type "file" imports. The file name is the caption.

  • box: Videos and images in the user's Box. Pass a folder id as container_id to list inside it (root when omitted); items with type "folder" are subfolders, only type "file" imports. The file name is the caption.

  • frameio: Videos and images in the user's Frame.io. Pass a folder id as container_id to list inside it (root when omitted); items with type "folder" are subfolders, only type "file" imports. The file name is the caption.

Input Schema

NameRequiredDescriptionDefault
queryNoSearch text, for sources that support it (canva).
cursorNonext_cursor from the previous page.
sourceNoOmit to list sources.
optionsNoList options for the source, e.g. { range: "30d" } for twitch.
container_idNoA project id from this tool's containers, or for onedrive and box a folder id (an item with type folder); the root when omitted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / source / enum
      Previous value: -[
-  "canva",
-  "opusclip",
-  "klap",
-  "twitch",
-  "heygen",
-  "descript",
-  "onedrive",
-  "box"
-]New value: +[
+  "canva",
+  "opusclip",
+  "klap",
+  "twitch",
+  "heygen",
+  "descript",
+  "onedrive",
+  "box",
+  "frameio"
+]
  2. Changed2 schema fields changed
    • changedInput schema / properties / container_id / description
      Previous value: -"A project id from this tool's containers."New value: +"A project id from this tool's containers, or for onedrive and box a folder id (an item with type folder); the root when omitted."
    • changedInput schema / properties / source / enum
      Previous value: -[
-  "canva",
-  "opusclip",
-  "klap",
-  "twitch",
-  "heygen"
-]New value: +[
+  "canva",
+  "opusclip",
+  "klap",
+  "twitch",
+  "heygen",
+  "descript",
+  "onedrive",
+  "box"
+]
  3. Added

TDQS

A4.7/5.0
Behavior5/5

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

The annotations already declare readOnlyHint, openWorldHint, and destructiveHint=false, but the description adds substantial behavior: connection prerequisites, pagination via next_cursor, container traversal for has_containers sources, and per-source item characteristics. It also covers source-specific defaults and constraints without contradicting the annotations.

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 description is front-loaded with general behavior before the source-specific bullets, and each source note carries practical detail. It is still lengthy and somewhat repetitive, such as repeated 'Projects first' phrasing, so it is comprehensive but not maximally concise.

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?

For a complex nine-source listing tool with no output schema, the description covers connection state, pagination, container traversal, per-source item types, and option defaults. That is sufficient for an agent to call the tool correctly without needing additional structured return-value documentation.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaningful semantics beyond the schema. It explains the source enum values, per-source options such as format, range, and version, container_id behavior for projects and folders, and how cursor maps to next_cursor.

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 states a specific verb ('Browses') and resource ('content the user can import') and explains both modes: omitting source lists connected sources, while supplying source lists that source's items. It clearly distinguishes listing from importing, so it is distinguishable from sibling tools such as import_items.

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 mode-selection guidance: omit source to discover sources, provide source to list items, and pass container_id for projects or folders. It also instructs the agent to tell users to connect unavailable sources in Settings > Integrations. It does not explicitly name import_items as the follow-up tool for importing selected items, so it falls short of a perfect 5.

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