Clip Studio MCP

quote_talking_short

Read-only

Quote a Talking Short. Does not render. captionMode defaults to current and does not change the quote. phrase is MCP-ungated. The Phrase chip is operator-email only in the workspace. hook remains accepted and burns Current karaoke. Optional hookTemplateId seeds the brief from Opening hooks and does not change the quote.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	No	Product page URL. Required unless brief is set.
`brief`	No	Product brief. Required unless url is set. An explicit brief wins over an Opening hooks seed.
`voice`	No	Narration voice id from list_audio_lab_voices. Defaults to the product default voice.
`script`	No	Talking-head script. Pass the researched or edited script.
`actorId`	No	Catalog creator id from list_talking_short_actors.
`angleId`	No	Angle id from research_talking_short. Defaults to angle-1 when omitted.
`hookBlanks`	No	Fill [bracket] keys from the Opening hooks seed. Example: { "the annoying thing": "soggy leftovers" }. Does not change the quote.
`hookIntent`	No	Optional Opening hooks intent. Browse with list_hook_bank. Ignored when seeding if hookTemplateId is set.
`aspectRatio`	No	Frame size. Talking Shorts is 9:16 vertical.
`captionMode`	No	Off, Current karaoke (default), or Phrase overlays. phrase is MCP-ungated for any caller. The Phrase chip is operator-email only in the Talking Shorts workspace. hook remains accepted and burns Current karaoke (Talking Shorts has no hook_kinetic). English only. Does not change the quote amount.	current
`faceImageUrl`	No	Optional public face still URL when not using a catalog actorId.
`hookTemplateId`	No	Optional Opening hooks template (catalog id hook_bank). The workspace picker is hidden. Seeds topic or Talking Shorts brief when that field is empty. Fill [brackets] via hookBlanks or by editing the seeded text. This is a script opening, not a caption look (captionStyle). Does not change the quote, consume, or refund.
`captionsEnabled`	No	Legacy on/off. Prefer captionStyle. false selects Off captions.
`durationSeconds`	No	Clip length in seconds. 15, 20, or 25. Defaults to 20.
`ugcFinishEnabled`	No	Phone-cam finish on the exported MP4. Defaults on. Does not change the quote.

Output Schema

TableJSON Schema

Name	Required	Description
`credits`	No	Usage this quote would consume from this month’s generation allowance (internal units).
`quoteId`	Yes	Quote id. Pass this to the matching generate tool. Quotes expire.
`expiresAt`	No	ISO timestamp when this quote expires.
`pricingVersion`	No	Pricing version used for this quote.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 20, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond annotations (readOnlyHint=true, destructiveHint=false), the description discloses key behaviors: it does not render, several parameters (captionMode, hookTemplateId, ugcFinishEnabled) do not change the quote, phrase is MCP-ungated while the Phrase chip is operator-email only, and hook 'burns Current karaoke' – a side effect the annotations alone do not convey. This adds real context for safe invocation.

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 about five sentences, compact and front-loaded with the core purpose ('Quote a Talking Short. Does not render.'). Each sentence adds a meaningful behavioral detail. It avoids verbosity but is slightly dense, packing multiple caveats in a short space.

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?

Given 15 optional parameters, a 100% schema coverage, and an output schema, the description covers the essential purpose, non-rendering behavior, key side effects, and access constraints. It could be more explicit about when to use this vs. generate_talking_short or other quote tools, but the name and first sentence largely cover that. Overall, it is sufficient for an agent to call 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 coverage is 100%, so each parameter is documented. The description adds meaning to specific parameters: captionMode defaults and does not change the quote, hookTemplateId seeds the brief without changing the quote, phrase has MCP-ungated access, and hook burns karaoke. These enrich understanding beyond the schema's simple field types.

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 'Quote a Talking Short' – a specific verb, resource, and type. 'Does not render' immediately distinguishes it from generate_talking_short. The name itself aligns with sibling quote_* tools, and the content clarifies it is for obtaining a quote, not producing media.

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?

The tool's purpose and name imply when to use it (for pricing a Talking Short), and 'Does not render' rules out generation. However, it does not explicitly state 'use this when you need a quote for a Talking Short' or contrast with other quote_* tools, though the name and purpose make it fairly evident.

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 tools Inspect

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

Need Help?