Skip to main content
Glama

studio_generate

Generate a piece of content with a Studio format (see studio_formats for the formats, their credit prices and the inputs they need). It spends the credits shown by studio_formats for the chosen duration (and quality, where the format has a Standard and a Premium price): always tell the user the price and get their confirmation first. The script, on-screen text and visuals are written from the brand profile and what you pass (hook, angle, prompt, or the user's own script). Generation runs in the background (seconds for images and text posts, a few minutes for videos and talking heads): this returns a generationId, then call studio_status with it. Results are saved to the media library and can be attached to posts. If the generation fails, the credits are given back. To use one of the user's saved recipes (studio_recipes), pass its recipeId: its format and settings are filled in, what you pass yourself wins. Pass formatId or recipeId. To make a finished generation again ("the same in Premium", "again at 30 s"), pass its id as fromGenerationId with only what changes: its format, words and settings are reused. Made for a post of the user's content plan (the chat names its planItemId): pass planItemId, the result becomes that post's content when it has none yet and is in the post's format (linkedToPlan says whether it did).

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": "studio_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
adNoStatic ads only: the parts the user writes (studio_formats "inputs" says which ones a format needs).
hookNoA hook formula key from studio_formats, or the hook in the user’s own words
angleNoThe angle or message to push
musicNoBackground music of a video, free: "auto" (the default: a library track matched to the post on video clips, slideshows, walls of text and hook + demo; none where a voice speaks), "none", or a library track id (upbeat-1, upbeat-2, upbeat-3, chill-1, chill-2, chill-3, corporate-1, corporate-2, corporate-3, cinematic-1, cinematic-2, cinematic-3, acoustic-1, acoustic-2, acoustic-3, electronic-1, electronic-2, electronic-3, hiphop-1, hiphop-2, hiphop-3, luxury-1, luxury-2, luxury-3, playful-1, playful-2, playful-3, ambient-1, ambient-2, ambient-3).
themeNoExplainers only: the look of the graphics, "night" (tech, creators, marketing, anything premium or modern), "paper" (editorial: finance, law, health, education, B2B, wellness), "bold" (loud and fun: fitness, food, retail, events, youth brands), "notebook" (teachers and coaches: study tips, how-tos, personal development). Left out, the plan picks one for the brand and avoids the brand's recent ones.
voiceNoA voice by name (studio_options "voices"): who speaks in talking heads, explainers, stories and voiceovers. Left out, the presenter’s own or matched voice.
aspectNoThe frame, where the format offers several (studio_formats "aspects"); left out, the format’s default.
promptNoWhat the content is about, in plain words
scriptNoThe user’s own script, used word for word
slidesNoSlideshow only: number of slides
effectsNoTalking heads only: animated effects around the presenter (studio_options "effects"): "none" (the default), "auto" (two or three picked for the script) or one effect id. Any choice but none adds its credits.
qualityNoFormats with "qualities" in studio_formats (talking heads, hook + demo, video clip, animated stories): "premium" uses the more realistic video model at its own credit price, "standard" (the default) the cheaper one. Ignored by other formats.
avatarIdNoAn avatar id from studio_formats, to keep the same AI creator
captionsNoBurn captions into videos (on by default where the format uses them)
formatIdNoThe format id from studio_formats (can be left out when recipeId is given)
languageNoThe language the post is written and spoken in (ISO 639-1); left out, the brand’s content language
mediaIdsNoMedia library ids: the product image or demo video the format needs; making_of: the 2 to 6 stage photos, in the order of the work
recipeIdNoA saved recipe id from studio_recipes: its format and settings are the defaults, anything else you pass wins
structureNoTalking heads and voiceovers: how the script is built. "free" (the default) leaves it to the writer, "payoff" holds the hook to one promise the video keeps and ends on one call to action, "reloops" does the same with curiosity loops (short question lines answered right away) inside the payoff. Ignored by other formats and when a script is given.
textStyleNoSlideshows and walls of text: how on-screen words are drawn ("box_white", "box_black" or "outline"). Left out, the format’s default.
planItemIdNoThe content-plan post this is made for: the result is linked to it
durationSecNoOne of the format’s durations
fromGenerationIdNoA generation to make again: its format and inputs are the defaults, anything else you pass wins (leave formatId and recipeId out)

Output Schema

NameRequiredDescriptionDefault
errorNo
creditsNo
generationIdNo
linkedToPlanNoWith planItemId: whether the plan post now has this generation as its content

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / formatId / enum
      Previous value: -[
      -  "wall_of_text",
      -  "slideshow",
      -  "ugc_talking_head",
      -  "street_interview",
      -  "yapper",
      -  "podcast_clip",
      -  "explainer",
      -  "story_claymation",
      -  "story_3d",
      -  "story_comic",
      -  "story_chalkboard",
      -  "story_anime",
      -  "story_papercraft",
      -  "story_cartoon_history",
      -  "ad_review",
      -  "ad_chat",
      -  "ad_product_hero",
      -  "ad_bold_poster",
      -  "ad_search",
      -  "ad_app_mockup",
      -  "hook_plus_demo",
      -  "spoken_hook_plus_demo",
      -  "making_of",
      -  "voiceover",
      -  "image_fast",
      -  "image_quality",
      -  "image_pro",
      -  "video_clip",
      -  "avatar_create"
      -]New value: +[
      +  "wall_of_text",
      +  "slideshow",
      +  "ugc_talking_head",
      +  "street_interview",
      +  "yapper",
      +  "podcast_clip",
      +  "explainer",
      +  "story_claymation",
      +  "story_3d",
      +  "story_comic",
      +  "story_chalkboard",
      +  "story_anime",
      +  "story_papercraft",
      +  "story_cartoon_history",
      +  "ad_review",
      +  "ad_chat",
      +  "ad_product_hero",
      +  "ad_bold_poster",
      +  "ad_search",
      +  "ad_app_mockup",
      +  "hook_plus_demo",
      +  "spoken_hook_plus_demo",
      +  "making_of",
      +  "listing_tour",
      +  "try_on",
      +  "voiceover",
      +  "image_fast",
      +  "image_quality",
      +  "image_pro",
      +  "video_clip",
      +  "avatar_create"
      +]
  2. Changed3 schema fields changed
    • changedInput schema / properties / formatId / enum
      Previous value: -[
      -  "wall_of_text",
      -  "slideshow",
      -  "ugc_talking_head",
      -  "street_interview",
      -  "yapper",
      -  "podcast_clip",
      -  "explainer",
      -  "story_claymation",
      -  "story_3d",
      -  "story_comic",
      -  "story_chalkboard",
      -  "story_anime",
      -  "story_papercraft",
      -  "story_cartoon_history",
      -  "ad_review",
      -  "ad_chat",
      -  "ad_product_hero",
      -  "ad_bold_poster",
      -  "ad_search",
      -  "ad_app_mockup",
      -  "hook_plus_demo",
      -  "spoken_hook_plus_demo",
      -  "voiceover",
      -  "image_fast",
      -  "image_quality",
      -  "image_pro",
      -  "video_clip",
      -  "avatar_create"
      -]New value: +[
      +  "wall_of_text",
      +  "slideshow",
      +  "ugc_talking_head",
      +  "street_interview",
      +  "yapper",
      +  "podcast_clip",
      +  "explainer",
      +  "story_claymation",
      +  "story_3d",
      +  "story_comic",
      +  "story_chalkboard",
      +  "story_anime",
      +  "story_papercraft",
      +  "story_cartoon_history",
      +  "ad_review",
      +  "ad_chat",
      +  "ad_product_hero",
      +  "ad_bold_poster",
      +  "ad_search",
      +  "ad_app_mockup",
      +  "hook_plus_demo",
      +  "spoken_hook_plus_demo",
      +  "making_of",
      +  "voiceover",
      +  "image_fast",
      +  "image_quality",
      +  "image_pro",
      +  "video_clip",
      +  "avatar_create"
      +]
    • changedInput schema / properties / mediaIds / description
      Previous value: -"Media library ids: the product image or demo video the format needs"New value: +"Media library ids: the product image or demo video the format needs; making_of: the 2 to 6 stage photos, in the order of the work"
    • changedInput schema / properties / mediaIds / maxItems
      Previous value: -4New value: +6
  3. Changed3 schema fields changed
    • addedInput schema / properties / fromGenerationId
      Added value: +{
      +  "description": "A generation to make again: its format and inputs are the defaults, anything else you pass wins (leave formatId and recipeId out)",
      +  "type": "string"
      +}
    • addedInput schema / properties / planItemId
      Added value: +{
      +  "description": "The content-plan post this is made for: the result is linked to it",
      +  "type": "string"
      +}
    • addedOutput schema / properties / linkedToPlan
      Added value: +{
      +  "description": "With planItemId: whether the plan post now has this generation as its content",
      +  "type": "boolean"
      +}
  4. Changed2 schema fields changed
    • addedInput schema / properties / ad
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Static ads only: the parts the user writes (studio_formats \"inputs\" says which ones a format needs).",
      +  "properties": {
      +    "chatApp": {
      +      "description": "Chat screenshot ads: the app it looks like",
      +      "enum": [
      +        "imessage",
      +        "whatsapp"
      +      ],
      +      "type": "string"
      +    },
      +    "contact": {
      +      "description": "Chat screenshot ads: the contact name at the top",
      +      "maxLength": 40,
      +      "type": "string"
      +    },
      +    "cta": {
      +      "description": "Static ads: the button text",
      +      "maxLength": 40,
      +      "type": "string"
      +    },
      +    "messages": {
      +      "description": "Chat screenshot ads: the conversation, one message per line (\"Me: …\" / \"Them: …\")",
      +      "maxLength": 2000,
      +      "type": "string"
      +    },
      +    "quotes": {
      +      "description": "Real customer quotes the user gave you, word for word: never write one yourself",
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "name": {
      +            "maxLength": 60,
      +            "type": "string"
      +          },
      +          "text": {
      +            "maxLength": 400,
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "text"
      +        ],
      +        "type": "object"
      +      },
      +      "maxItems": 3,
      +      "type": "array"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / textStyle
      Added value: +{
      +  "description": "Slideshows and walls of text: how on-screen words are drawn (\"box_white\", \"box_black\" or \"outline\"). Left out, the format’s default.",
      +  "enum": [
      +    "outline",
      +    "box_white",
      +    "box_black"
      +  ],
      +  "type": "string"
      +}
  5. Changed5 schema fields changed
    • addedInput schema / properties / aspect
      Added value: +{
      +  "description": "The frame, where the format offers several (studio_formats \"aspects\"); left out, the format’s default.",
      +  "enum": [
      +    "9:16",
      +    "4:5",
      +    "1:1",
      +    "16:9"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / effects
      Added value: +{
      +  "description": "Talking heads only: animated effects around the presenter (studio_options \"effects\"): \"none\" (the default), \"auto\" (two or three picked for the script) or one effect id. Any choice but none adds its credits.",
      +  "enum": [
      +    "none",
      +    "auto",
      +    "data-split",
      +    "liquid-glass-graph",
      +    "broll-split",
      +    "messages",
      +    "tap",
      +    "comment-box",
      +    "spotlight",
      +    "backdrop-word",
      +    "glitter-spotlight",
      +    "comment-cta",
      +    "comment-drop",
      +    "orbit",
      +    "place-in-grid",
      +    "checklist"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / formatId / enum
      Previous value: -[
      -  "wall_of_text",
      -  "slideshow",
      -  "ugc_talking_head",
      -  "street_interview",
      -  "yapper",
      -  "podcast_clip",
      -  "story_claymation",
      -  "story_3d",
      -  "story_comic",
      -  "story_chalkboard",
      -  "story_anime",
      -  "story_papercraft",
      -  "ad_review",
      -  "ad_chat",
      -  "ad_product_hero",
      -  "ad_bold_poster",
      -  "ad_search",
      -  "ad_app_mockup",
      -  "hook_plus_demo",
      -  "spoken_hook_plus_demo",
      -  "voiceover",
      -  "image_fast",
      -  "image_quality",
      -  "image_pro",
      -  "video_clip",
      -  "avatar_create"
      -]New value: +[
      +  "wall_of_text",
      +  "slideshow",
      +  "ugc_talking_head",
      +  "street_interview",
      +  "yapper",
      +  "podcast_clip",
      +  "explainer",
      +  "story_claymation",
      +  "story_3d",
      +  "story_comic",
      +  "story_chalkboard",
      +  "story_anime",
      +  "story_papercraft",
      +  "story_cartoon_history",
      +  "ad_review",
      +  "ad_chat",
      +  "ad_product_hero",
      +  "ad_bold_poster",
      +  "ad_search",
      +  "ad_app_mockup",
      +  "hook_plus_demo",
      +  "spoken_hook_plus_demo",
      +  "voiceover",
      +  "image_fast",
      +  "image_quality",
      +  "image_pro",
      +  "video_clip",
      +  "avatar_create"
      +]
    • addedInput schema / properties / theme
      Added value: +{
      +  "description": "Explainers only: the look of the graphics, \"night\" (tech, creators, marketing, anything premium or modern), \"paper\" (editorial: finance, law, health, education, B2B, wellness), \"bold\" (loud and fun: fitness, food, retail, events, youth brands), \"notebook\" (teachers and coaches: study tips, how-tos, personal development). Left out, the plan picks one for the brand and avoids the brand's recent ones.",
      +  "enum": [
      +    "night",
      +    "paper",
      +    "bold",
      +    "notebook"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / voice
      Added value: +{
      +  "description": "A voice by name (studio_options \"voices\"): who speaks in talking heads, explainers, stories and voiceovers. Left out, the presenter’s own or matched voice.",
      +  "maxLength": 64,
      +  "type": "string"
      +}
  6. Changed1 schema field changed
    • addedInput schema / properties / structure
      Added value: +{
      +  "description": "Talking heads and voiceovers: how the script is built. \"free\" (the default) leaves it to the writer, \"payoff\" holds the hook to one promise the video keeps and ends on one call to action, \"reloops\" does the same with curiosity loops (short question lines answered right away) inside the payoff. Ignored by other formats and when a script is given.",
      +  "enum": [
      +    "free",
      +    "payoff",
      +    "reloops"
      +  ],
      +  "type": "string"
      +}
  7. Changed1 schema field changed
    • changedInput schema / properties / formatId / enum
      Previous value: -[
      -  "wall_of_text",
      -  "slideshow",
      -  "ugc_talking_head",
      -  "street_interview",
      -  "yapper",
      -  "podcast_clip",
      -  "story_claymation",
      -  "story_3d",
      -  "story_comic",
      -  "story_chalkboard",
      -  "story_anime",
      -  "story_papercraft",
      -  "ad_review",
      -  "ad_chat",
      -  "ad_product_hero",
      -  "ad_bold_poster",
      -  "ad_search",
      -  "ad_app_mockup",
      -  "hook_plus_demo",
      -  "voiceover",
      -  "image_fast",
      -  "image_quality",
      -  "image_pro",
      -  "video_clip",
      -  "avatar_create"
      -]New value: +[
      +  "wall_of_text",
      +  "slideshow",
      +  "ugc_talking_head",
      +  "street_interview",
      +  "yapper",
      +  "podcast_clip",
      +  "story_claymation",
      +  "story_3d",
      +  "story_comic",
      +  "story_chalkboard",
      +  "story_anime",
      +  "story_papercraft",
      +  "ad_review",
      +  "ad_chat",
      +  "ad_product_hero",
      +  "ad_bold_poster",
      +  "ad_search",
      +  "ad_app_mockup",
      +  "hook_plus_demo",
      +  "spoken_hook_plus_demo",
      +  "voiceover",
      +  "image_fast",
      +  "image_quality",
      +  "image_pro",
      +  "video_clip",
      +  "avatar_create"
      +]
  8. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false) the description discloses credit spending, the requirement to tell the user the price and get confirmation, asynchronous background execution with a generationId handle, refunds on failure, and saving to the media library. What is not covered is how long results persist or any concurrency/queuing limits, but the mutation and cost profile — the risky part — is fully spelled out.

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?

Long, but the length is justified by 23 parameters and several mutually exclusive creation paths, and the purpose is front-loaded in the first sentence. The "anything else you pass wins" rule is repeated for recipeId, planItemId and fromGenerationId, which is redundant though arguably useful as a consistent pattern, and the indented multi-paragraph formatting is slightly awkward.

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, credit-spending, asynchronous, 23-parameter tool this covers everything an agent needs to call it correctly: prerequisites, cost confirmation, which sibling resolves the format, how to poll, what happens on failure, and how the result is stored and linked. An output schema exists, so the description's brief mention of generationId and linkedToPlan is a bonus rather than a gap.

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 the baseline is 3, and the description earns above that by adding cross-parameter precedence rules the schema cannot express: recipeId defaults overridden by anything explicitly passed, fromGenerationId reusing format and inputs "with only what changes", and planItemId linking the result to a post when it has none. Individual parameter meaning is already in the schema, so it stops short of 5.

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 and resource — "Generate a piece of content with a Studio format" — and immediately points to studio_formats as the source of the formats. It is clearly distinct from the plain image/video generators among the siblings, and the naming of formatId/recipeId shows what drives generation.

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 names the alternatives and the conditions that select them: studio_formats for formats and prices, studio_status to poll the returned generationId, studio_recipes via recipeId, and re-running a prior output via fromGenerationId. It also states the when-not rules ("Pass formatId or recipeId", "leave formatId and recipeId out" when using fromGenerationId).

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources