Skip to main content
Glama

Clip Studio MCP

by ai.clipstudio
OverviewDiscussionsAdmin

get_topic_short

Read-only

Fetch a Topic Short generation, including captionBurn persisted on the completed record. status moves through queued and in_progress, then composing while the final edit is put together, then completed or failed; keep polling through composing. setup echoes the options it was made with (format, frame size, language, visual style and render tier, host, sources, voice clone, series episode). A sourced short also returns sources: the citations shown on its Sources card. shots lists each shot with its judged alternates for swap_shot edits. On a completed short it also returns versions (the original plus each edit; current marks the one the library shows), editCapabilities (including musicOptions for edit_topic_short) and publication (which version a public page is pinned to). On a completed short it also returns postingPack (title, caption, hashtags), coverUrl when the cover is ready, and exports (each format and whether export_topic_short can make it).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesTopic Short generation id from generate_topic_short.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoTopic Short generation id.
setupNoThe setup this short was made with: storyFormat, aspectRatio, language, visualStyle, renderTier, aiHook, characters, hostNarratorId, sourced, sourceInputs, voiceCloneId, seriesId and seriesEpisodeId (omitted fields are the defaults).
shotsNoCompleted short, when recorded: per-shot picks by beatIndex and shotIndex with judged alternates. An alternate id is the alternateId edit_topic_short kind swap_shot takes.
statusNoJob status: submitting, queued, in_progress, composing (the voiceover and shots are done and the final edit is being put together), completed, or failed. Keep polling while it is composing.
exportsNoWhen the posting pack is on: each export format and whether export_topic_short can make it for this short.
sourcesNoSourced shorts only, once completed: the cited sources behind the narration (title, publisher, url, accessedAt), as shown on the clip page Sources card.
videoIdNoLibrary clip id for this job, when one exists.
coverUrlNoCover still URL (opening frame), once export_topic_short format cover has made it.
versionsNoCompleted short only, when edits are on: version 0 is the original, then one per edit_topic_short call (editId, version, kind, status, outputUrl, current, published).
outputUrlNoDownload or playback URL when the job has finished.
captionBurnNoPersisted caption-burn record on a completed short, when present.
postingPackNoWhen the posting pack is on: suggested title, caption and hashtags for posting this short.
publicationNoWhen edits are on: whether a public page exists and which version it is pinned to.
editCapabilitiesNoWhen edits are on: whether captions and music can be edited, musicOptions (id, mood, previewUrl) for edit_topic_short, and freeEditsRemaining.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • addedOutput schema / properties / coverUrl
      Added value: +{
+  "description": "Cover still URL (opening frame), once export_topic_short format cover has made it.",
+  "type": "string"
+}
    • addedOutput schema / properties / editCapabilities
      Added value: +{
+  "additionalProperties": true,
+  "description": "When edits are on: whether captions and music can be edited, musicOptions (id, mood, previewUrl) for edit_topic_short, and freeEditsRemaining.",
+  "type": "object"
+}
    • addedOutput schema / properties / exports
      Added value: +{
+  "description": "When the posting pack is on: each export format and whether export_topic_short can make it for this short.",
+  "items": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / postingPack
      Added value: +{
+  "additionalProperties": true,
+  "description": "When the posting pack is on: suggested title, caption and hashtags for posting this short.",
+  "type": "object"
+}
    • addedOutput schema / properties / publication
      Added value: +{
+  "additionalProperties": true,
+  "description": "When edits are on: whether a public page exists and which version it is pinned to.",
+  "type": "object"
+}
    • addedOutput schema / properties / setup
      Added value: +{
+  "additionalProperties": true,
+  "description": "The setup this short was made with: storyFormat, aspectRatio, language, visualStyle, renderTier, aiHook, characters, hostNarratorId, sourced, sourceInputs, voiceCloneId, seriesId and seriesEpisodeId (omitted fields are the defaults).",
+  "type": "object"
+}
    • addedOutput schema / properties / shots
      Added value: +{
+  "description": "Completed short, when recorded: per-shot picks by beatIndex and shotIndex with judged alternates. An alternate id is the alternateId edit_topic_short kind swap_shot takes.",
+  "items": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "type": "array"
+}
    • addedOutput schema / properties / sources
      Added value: +{
+  "description": "Sourced shorts only, once completed: the cited sources behind the narration (title, publisher, url, accessedAt), as shown on the clip page Sources card.",
+  "items": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "type": "array"
+}
    • changedOutput schema / properties / status / description
      Previous value: -"Job status such as pending, queued, in_progress, completed, or failed."New value: +"Job status: submitting, queued, in_progress, composing (the voiceover and shots are done and the final edit is being put together), completed, or failed. Keep polling while it is composing."
    • addedOutput schema / properties / versions
      Added value: +{
+  "description": "Completed short only, when edits are on: version 0 is the original, then one per edit_topic_short call (editId, version, kind, status, outputUrl, current, published).",
+  "items": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "type": "array"
+}
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real behavioral value beyond them: the full status state machine (queued → in_progress → composing → completed/failed) and the explicit instruction to keep polling during composing, which prevents premature abandonment. It does not mention auth scope, rate limits, or what happens for an unknown id.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is front-loaded and efficient, but the remainder is a long enumeration of returned fields (setup, sources, shots, versions, editCapabilities, publication, postingPack, coverUrl, exports) that largely duplicates the output schema. Roughly two-thirds of the text is redundant with structured data that the agent already receives.

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 a read-and-poll endpoint with one required parameter, the description is more than sufficient: it explains the lifecycle, what triggers continued polling, and how to read the completed payload. Since an output schema exists, the field-by-field listing is surplus rather than a gap, and only error/not-found behavior is missing.

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% and the single 'id' parameter is already documented in the schema as coming from generate_topic_short. The description repeats that same fact rather than adding format, constraints, or validity semantics, so the baseline 3 for a fully-covered schema applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause states a specific verb and resource ('Fetch a Topic Short generation'), which separates it cleanly from write siblings like generate_topic_short and edit_topic_short. It never names the closest read alternative (get_talking_short or get_public_generation), so the differentiation is by name only rather than explicit routing.

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?

'keep polling through composing' is genuine operational guidance that tells the agent this is a re-invoked status endpoint, not a one-shot fetch. There is no explicit when-not or alternative-tool routing, which keeps it out of the top band.

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

All Clip Studio MCP 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