Skip to main content
Glama

Write a music video shot list

plan_music_video

The director's shot list for a music video, the idea and every shot, before anything is charged Free (a limited number an hour). Takes about a minute. Returns a plan: the concept, the character it keeps the artist from, and its shots (cut between the song's lines, up to about 14 seconds each) with their lyrics and how each comes in (a cut, or carrying on in a continuous take). Show it to the user, rewrite it with revise until they like it, then quote_music_video and create_music_video with its plan_id.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "song_id": "<song_id>"
    },
    "name": "plan_music_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
castNoThe performer in it, kept from their character: what they wear, outfit_kit (a kit outfit's @handle, without the @, worn in every shot they are in); left out, the director picks. Only when the performer is on screen
trimNoOnly this section of the song (15 seconds to 10 minutes); omitted, the whole song (15 seconds to 10 minutes long). Best: a part from get_song_analysis (parts[]: its start and end never cut a word)
modelNoThe music video model: one-take (default; MiniMax H3 Max), seedance-2-0, seedance-2-0-fast, seedance-2-0-mini or seedance-2-5. get_options lists the models offered to you with the categories, styles, formats, takes and length each makes, and guide: what each is best for, its strengths, weaknesses and public benchmark scores. When the person hasn't named a model, suggest the kind's recommended_model (get_options music_video.categories) with its best_for line and the price difference between models from quotes, and let them choose anyone-take
styleNoOptional visual style (get_options: music_video.styles); omitted, the director picks one from the cover
takesNoHow the shots meet: "cuts" (default: shots meet with a cut between the song's lines, like an edit) or "continuous" (the director may carry a shot on into the next through a picture drawn of the moment they meet, priced per picture; the quote before a plan counts every join, the plan's quote only the ones it draws)cuts
peopleNo
reviseNoRewrite an earlier plan of this song: {"plan_id":"plan_…","note":"what to change"} (the next draft). It keeps that plan's brief (model, format, style, direction, people, section…): send song_id and revise alone, or with only the brief fields to change
scenesNoWhere it is set besides the places the direction mentions from the kit: {"mode":"invent"} (default: the director imagines the others) or {"mode":"stock"} (it finds a real stock photo of each place it writes, empty of people, and the artist is put into it), up to the model's kit.places in all
lipsyncNo"auto" (default: the director has the artist sing the important lines on camera) or "never" (nobody sings on camera; the song plays over every shot). A kind sung on camera (lyric-led) refuses "never"; an instrumental song never lip-syncsauto
look_idNoA music video Look (list_music_video_looks: one made public, or the workspace's own) the video follows: its treatment leads the director and its places and props join the kit. Send its category, style, takes and lipsync too (or your own)
song_idYesThe song; its artist performs the video and needs their character (list_characters; start_character makes one), unless performer names another character
categoryNoperformance (default), intercut, cinematic, story or surrealperformance
kit_onlyNoOnly what the kit's pictures show: no place, prop, person or lighting change beyond them (every shot in one of the kit's places, lit as in its picture; only the props and the people the brief names). Omitted: on when the brief mentions a kit piece by @handle (an outfit, a place or a prop), off otherwise; send false to let the director add to the kit
cast_modeNoWho else may be on screen besides the performer and people: "director" (default when left out: the director may cast up to 3 more, each drawn as a character sheet only after the user says yes: cast_music_video) or "exact" (only who was picked; the song's other people are carried by the scene, an empty chair or a coat left out, never shown). Nobody appears on screen without a character sheet; with nobody cast, crowds and dancers are faceless. A cast-story video with "exact" needs people
directionNoOptional notes for the director (a place, an era, a story idea, a mood). Mention kit pieces by @handle (list_kit): "@nina-kazora in the @blue-set on the @rooftop, the @chrome-mic in hand"; a mentioned piece is used exactly as it is and the director designs the rest. Mention characters by @handle (list_characters) to put them in the shots beside the performer (those in the song's artist's kit and those other artists shared, list_characters with for_artist_id; the song's artist's own too when another character performs; in a story with a cast, they are the cast): "@mia-torres dances behind her in the last chorus". An unknown handle, or another artist's piece they haven't shared, answers 400. Pin a change to a moment with a sentence that says on "<words sung>" (on every "…" for each time they are sung) or at m:ss (the song's time), for example: On "Drop it" cut to @rooftop-club. / @grandma appears on "She said yes". / At 1:05 the lights go out. A shot starts exactly there (the plan has one more shot when the usual cut runs over it), set in the first kit place the sentence names, with the characters it names appearing in it (and not in the shot before); shots[].cue shows it. Words the section doesn't sing, or two moments under 2 seconds apart, answer 400
on_screenNoWho is on screen: artist (the song's artist, from their character; in a Creator workspace the character performer names), cast (people the director casts and describes; the artist needn't appear) or none (places, light and objects). Omitted: the kind's (cast-story a cast, mood and places no one, else the artist). Only what the model makes: get_options lists on_screen per model (cast and none are offered once a model is tested with them). Without the artist no character is needed and there are no outfits; continuous takes join on the cast and the place
performerNoOnly in a Creator workspace (its projects have no character of their own): who performs (sings to camera lip-synced, or plays), a character in the song's project's kit or one another project shared (list_characters with for_artist_id: its id, kit_…). Anywhere else the song's artist performs, from their character: leave it out. Only when someone performs (on_screen artist: every kind but cast-story, mood and places).
lookbook_idNoA lookbook (design_music_video_shoot) whose kept, drawn pieces the video uses like the kit pieces the direction mentions; its idea leads the director
aspect_ratioNo"9:16" (default), "16:9" or "1:1"9:16

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / cast_mode
      Added value: +{
      +  "description": "Who else may be on screen besides the performer and people: \"director\" (default when left out: the director may cast up to 3 more, each drawn as a character sheet only after the user says yes: cast_music_video) or \"exact\" (only who was picked; the song's other people are carried by the scene, an empty chair or a coat left out, never shown). Nobody appears on screen without a character sheet; with nobody cast, crowds and dancers are faceless. A cast-story video with \"exact\" needs people",
      +  "enum": [
      +    "exact",
      +    "director"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / direction / description
      Previous value: -"Optional notes for the director (a place, an era, a story idea, a mood). Mention kit pieces by @handle (list_kit): \"@nina-kazora in the @blue-set on the @rooftop, the @chrome-mic in hand\"; a mentioned piece is used exactly as it is and the director designs the rest. Mention characters by @handle (list_characters) to put them in the shots beside the performer (those in the song's artist's kit and those other artists shared, list_characters with for_artist_id; the song's artist's own too when another character performs; in a story with a cast, they are the cast): \"@mia-torres dances behind her in the last chorus\". An unknown handle, or another artist's piece they haven't shared, answers 400"New value: +"Optional notes for the director (a place, an era, a story idea, a mood). Mention kit pieces by @handle (list_kit): \"@nina-kazora in the @blue-set on the @rooftop, the @chrome-mic in hand\"; a mentioned piece is used exactly as it is and the director designs the rest. Mention characters by @handle (list_characters) to put them in the shots beside the performer (those in the song's artist's kit and those other artists shared, list_characters with for_artist_id; the song's artist's own too when another character performs; in a story with a cast, they are the cast): \"@mia-torres dances behind her in the last chorus\". An unknown handle, or another artist's piece they haven't shared, answers 400. Pin a change to a moment with a sentence that says on \"<words sung>\" (on every \"…\" for each time they are sung) or at m:ss (the song's time), for example: On \"Drop it\" cut to @rooftop-club. / @grandma appears on \"She said yes\". / At 1:05 the lights go out. A shot starts exactly there (the plan has one more shot when the usual cut runs over it), set in the first kit place the sentence names, with the characters it names appearing in it (and not in the shot before); shots[].cue shows it. Words the section doesn't sing, or two moments under 2 seconds apart, answer 400"
    • addedInput schema / properties / kit_only
      Added value: +{
      +  "description": "Only what the kit's pictures show: no place, prop, person or lighting change beyond them (every shot in one of the kit's places, lit as in its picture; only the props and the people the brief names). Omitted: on when the brief mentions a kit piece by @handle (an outfit, a place or a prop), off otherwise; send false to let the director add to the kit",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / revise / description
      Previous value: -"Rewrite an earlier plan of this song: {\"plan_id\":\"plan_…\",\"note\":\"what to change\"} (the next draft)"New value: +"Rewrite an earlier plan of this song: {\"plan_id\":\"plan_…\",\"note\":\"what to change\"} (the next draft). It keeps that plan's brief (model, format, style, direction, people, section…): send song_id and revise alone, or with only the brief fields to change"
  2. Changed1 schema field changed
    • changedInput schema / properties / style / description
      Previous value: -"Optional look: natural, film, golden-hour, neon-night, noir, vintage or dreamy; omitted, the director picks one from the cover"New value: +"Optional visual style (get_options: music_video.styles); omitted, the director picks one from the cover"
  3. Changed1 schema field changed
    • changedInput schema / properties / model / description
      Previous value: -"The music video model: one-take (default; MiniMax H3 Max, the artist lip-synced in shots cut between the song's lines). get_options lists the models with the categories, styles, formats, takes and length each makes"New value: +"The music video model: one-take (default; MiniMax H3 Max), seedance-2-0, seedance-2-0-fast, seedance-2-0-mini or seedance-2-5. get_options lists the models offered to you with the categories, styles, formats, takes and length each makes, and guide: what each is best for, its strengths, weaknesses and public benchmark scores. When the person hasn't named a model, suggest the kind's recommended_model (get_options music_video.categories) with its best_for line and the price difference between models from quotes, and let them choose any"
  4. Changed1 schema field changed
    • changedInput schema / properties / on_screen / description
      Previous value: -"Who is on screen: artist (the song's artist, from their character; in a Creator workspace the character performer names), cast (people the director casts and describes; the artist needn't appear) or none (places, light and objects). Omitted: the kind's (cast-story a cast, mood and places no one, else the artist). Only what the model makes: get_options lists on_screen per model (cast and none are offered once a model is tested with them). Without the artist no character is needed, there are no outfits and no continuous takes"New value: +"Who is on screen: artist (the song's artist, from their character; in a Creator workspace the character performer names), cast (people the director casts and describes; the artist needn't appear) or none (places, light and objects). Omitted: the kind's (cast-story a cast, mood and places no one, else the artist). Only what the model makes: get_options lists on_screen per model (cast and none are offered once a model is tested with them). Without the artist no character is needed and there are no outfits; continuous takes join on the cast and the place"
  5. Changed3 schema fields changed
    • changedInput schema / properties / direction / description
      Previous value: -"Optional notes for the director (a place, an era, a story idea, a mood). Mention kit pieces by @handle (list_kit): \"@nina-kazora in the @blue-set on the @rooftop, the @chrome-mic in hand\"; a mentioned piece is used exactly as it is and the director designs the rest. Mention characters by @handle (list_characters) to put them in the shots beside the performer (any of the workspace's, the song's artist's own too when another character performs; in a story with a cast, they are the cast): \"@mia-torres dances behind her in the last chorus\". An unknown handle answers 400"New value: +"Optional notes for the director (a place, an era, a story idea, a mood). Mention kit pieces by @handle (list_kit): \"@nina-kazora in the @blue-set on the @rooftop, the @chrome-mic in hand\"; a mentioned piece is used exactly as it is and the director designs the rest. Mention characters by @handle (list_characters) to put them in the shots beside the performer (those in the song's artist's kit and those other artists shared, list_characters with for_artist_id; the song's artist's own too when another character performs; in a story with a cast, they are the cast): \"@mia-torres dances behind her in the last chorus\". An unknown handle, or another artist's piece they haven't shared, answers 400"
    • changedInput schema / properties / on_screen / description
      Previous value: -"Who is on screen: artist (the song's artist, from their character; in a Creator workspace the cast member performer names), cast (people the director casts and describes; the artist needn't appear) or none (places, light and objects). Omitted: the kind's (cast-story a cast, mood and places no one, else the artist). Only what the model makes: get_options lists on_screen per model (cast and none are offered once a model is tested with them). Without the artist no character is needed, there are no outfits and no continuous takes"New value: +"Who is on screen: artist (the song's artist, from their character; in a Creator workspace the character performer names), cast (people the director casts and describes; the artist needn't appear) or none (places, light and objects). Omitted: the kind's (cast-story a cast, mood and places no one, else the artist). Only what the model makes: get_options lists on_screen per model (cast and none are offered once a model is tested with them). Without the artist no character is needed, there are no outfits and no continuous takes"
    • changedInput schema / properties / performer / description
      Previous value: -"Only in a Creator workspace (its projects have no character of their own): who performs (sings to camera lip-synced, or plays), a character of its cast (list_characters: its id, kit_…). Anywhere else the song's artist performs, from their character: leave it out. Only when someone performs (on_screen artist: every kind but cast-story, mood and places)."New value: +"Only in a Creator workspace (its projects have no character of their own): who performs (sings to camera lip-synced, or plays), a character in the song's project's kit or one another project shared (list_characters with for_artist_id: its id, kit_…). Anywhere else the song's artist performs, from their character: leave it out. Only when someone performs (on_screen artist: every kind but cast-story, mood and places)."
  6. Changed15 schema fields changed
    • changedInput schema / properties / cast / description
      Previous value: -"The two photos the artist is kept from: face_photo_id (a sharp face, mouth visible) and outfit_photo_id (the outfit and body worn throughout); either left out, the director picks it. One photo can be both; hidden photos (add_artist_photos hidden) work too"New value: +"The performer in it, kept from their character: what they wear, outfit_kit (a kit outfit's @handle, without the @, worn in every shot they are in); left out, the director picks. Only when the performer is on screen"
    • removedInput schema / properties / cast / properties / face_photo_id
      Removed value: -{
      -  "pattern": "^photo_[0-9a-f-]{36}$",
      -  "type": "string"
      -}
    • addedInput schema / properties / cast / properties / outfit_kit
      Added value: +{
      +  "pattern": "^[a-z0-9-]{1,40}$",
      +  "type": "string"
      +}
    • removedInput schema / properties / cast / properties / outfit_photo_id
      Removed value: -{
      -  "pattern": "^photo_[0-9a-f-]{36}$",
      -  "type": "string"
      -}
    • changedInput schema / properties / category / enum
      Previous value: -[
      -  "performance",
      -  "intercut",
      -  "cinematic",
      -  "story",
      -  "surreal"
      -]New value: +[
      +  "performance",
      +  "intercut",
      +  "cinematic",
      +  "story",
      +  "surreal",
      +  "studio",
      +  "live",
      +  "instrument",
      +  "lyric-led",
      +  "vlog",
      +  "fashion",
      +  "oner",
      +  "cast-story",
      +  "mood",
      +  "places",
      +  "dance",
      +  "band",
      +  "action"
      +]
    • changedInput schema / properties / direction / description
      Previous value: -"Optional notes for the director (a place, an era, a story idea, a mood). Mention kit pieces by @handle (list_kit): \"@nina-kazora in the @blue-set on the @rooftop, the @chrome-mic in hand\"; a mentioned piece is used exactly as it is and the director designs the rest. An unknown handle answers 400"New value: +"Optional notes for the director (a place, an era, a story idea, a mood). Mention kit pieces by @handle (list_kit): \"@nina-kazora in the @blue-set on the @rooftop, the @chrome-mic in hand\"; a mentioned piece is used exactly as it is and the director designs the rest. Mention characters by @handle (list_characters) to put them in the shots beside the performer (any of the workspace's, the song's artist's own too when another character performs; in a story with a cast, they are the cast): \"@mia-torres dances behind her in the last chorus\". An unknown handle answers 400"
    • addedInput schema / properties / lipsync
      Added value: +{
      +  "default": "auto",
      +  "description": "\"auto\" (default: the director has the artist sing the important lines on camera) or \"never\" (nobody sings on camera; the song plays over every shot). A kind sung on camera (lyric-led) refuses \"never\"; an instrumental song never lip-syncs",
      +  "enum": [
      +    "auto",
      +    "never"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / look_id
      Added value: +{
      +  "description": "A music video Look (list_music_video_looks: one made public, or the workspace's own) the video follows: its treatment leads the director and its places and props join the kit. Send its category, style, takes and lipsync too (or your own)",
      +  "pattern": "^mvlook_[0-9a-f-]{36}$",
      +  "type": "string"
      +}
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "one-take"
      -]New value: +[
      +  "one-take",
      +  "seedance-2-0",
      +  "seedance-2-0-fast",
      +  "seedance-2-0-mini",
      +  "seedance-2-5"
      +]
    • addedInput schema / properties / on_screen
      Added value: +{
      +  "description": "Who is on screen: artist (the song's artist, from their character; in a Creator workspace the cast member performer names), cast (people the director casts and describes; the artist needn't appear) or none (places, light and objects). Omitted: the kind's (cast-story a cast, mood and places no one, else the artist). Only what the model makes: get_options lists on_screen per model (cast and none are offered once a model is tested with them). Without the artist no character is needed, there are no outfits and no continuous takes",
      +  "enum": [
      +    "artist",
      +    "cast",
      +    "none"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / people
      Added value: +{
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "character": {
      +        "pattern": "^[a-z0-9][a-z0-9-]{0,39}$",
      +        "type": "string"
      +      },
      +      "does": {
      +        "maxLength": 300,
      +        "minLength": 1,
      +        "type": "string"
      +      },
      +      "outfit": {
      +        "pattern": "^[a-z0-9][a-z0-9-]{0,39}$",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "character"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 8,
      +  "type": "array"
      +}
    • addedInput schema / properties / performer
      Added value: +{
      +  "description": "Only in a Creator workspace (its projects have no character of their own): who performs (sings to camera lip-synced, or plays), a character of its cast (list_characters: its id, kit_…). Anywhere else the song's artist performs, from their character: leave it out. Only when someone performs (on_screen artist: every kind but cast-story, mood and places).",
      +  "pattern": "^kit_[0-9a-f-]{36}$",
      +  "type": "string"
      +}
    • changedInput schema / properties / song_id / description
      Previous value: -"The song; its artist performs the video and needs photos (add_artist_photos)"New value: +"The song; its artist performs the video and needs their character (list_characters; start_character makes one), unless performer names another character"
    • changedInput schema / properties / style / enum
      Previous value: -[
      -  "natural",
      -  "film",
      -  "golden-hour",
      -  "neon-night",
      -  "noir",
      -  "vintage",
      -  "dreamy"
      -]New value: +[
      +  "natural",
      +  "film",
      +  "golden-hour",
      +  "neon-night",
      +  "noir",
      +  "vintage",
      +  "dreamy",
      +  "super-8",
      +  "vhs",
      +  "documentary",
      +  "glossy-pop",
      +  "indie",
      +  "cyberpunk",
      +  "y2k",
      +  "lofi",
      +  "painterly",
      +  "anime",
      +  "clay"
      +]
    • changedInput schema / properties / takes / description
      Previous value: -"How the shots meet: \"cuts\" (default: shots meet between the song's lines like an edit, with a cut or the transition the director picks at each join: dissolve, dip to black, flash or whip; ask for them, or for none, in direction) or \"continuous\" (the director may carry a shot on into the next through a picture drawn of the moment they meet, priced per picture; the quote before a plan counts every join, the plan's quote only the ones it draws)"New value: +"How the shots meet: \"cuts\" (default: shots meet with a cut between the song's lines, like an edit) or \"continuous\" (the director may carry a shot on into the next through a picture drawn of the moment they meet, priced per picture; the quote before a plan counts every join, the plan's quote only the ones it draws)"
  7. Changed2 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"The music video model: one-take (default; one continuous, lip-synced take of the artist). get_options lists the models with the categories, styles, formats and length each makes"New value: +"The music video model: one-take (default; MiniMax H3 Max, the artist lip-synced in shots cut between the song's lines). get_options lists the models with the categories, styles, formats, takes and length each makes"
    • addedInput schema / properties / takes
      Added value: +{
      +  "default": "cuts",
      +  "description": "How the shots meet: \"cuts\" (default: shots meet between the song's lines like an edit, with a cut or the transition the director picks at each join: dissolve, dip to black, flash or whip; ask for them, or for none, in direction) or \"continuous\" (the director may carry a shot on into the next through a picture drawn of the moment they meet, priced per picture; the quote before a plan counts every join, the plan's quote only the ones it draws)",
      +  "enum": [
      +    "cuts",
      +    "continuous"
      +  ],
      +  "type": "string"
      +}
  8. Changed1 schema field changed
    • changedInput schema / properties / trim / description
      Previous value: -"Only this section of the song (15 seconds to 10 minutes); omitted, the whole song (15 seconds to 10 minutes long)"New value: +"Only this section of the song (15 seconds to 10 minutes); omitted, the whole song (15 seconds to 10 minutes long). Best: a part from get_song_analysis (parts[]: its start and end never cut a word)"
  9. Added

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations, the description discloses that the plan is free but rate-limited per hour, takes about a minute, and is not charged until later steps. It also describes the returned plan's contents because there is no output schema. It does not spell out idempotency or plan persistence behavior, but the annotations already establish the safety profile.

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 and avoids unnecessary repetition; nearly every sentence contributes purpose, output, cost, or workflow. The phrasing is dense and slightly awkward in places, especially around 'Free (a limited number an hour)', but it remains efficient.

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 complex 19-parameter generation tool with no output schema, the description covers the essential purpose, return shape, cost behavior, and downstream workflow. The schema handles detailed parameter semantics, so no major agent-critical gap remains, though additional clarity on plan lifecycle could improve it.

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?

The input schema has very high description coverage and already explains the many parameters in detail, while the tool description only mentions plan_id and revise in the workflow. The description does not add meaningful semantics for the other inputs, so the baseline of 3 is appropriate.

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 clearly states that this tool produces a music video shot list: the idea, the character choice, and every shot with lyrics and transitions. It distinguishes the planning step from the later paid steps of quoting and creating the video, and it names the relevant siblings explicitly.

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?

It gives a precise workflow: generate the plan, show it to the user, rewrite it with revise until acceptable, then call quote_music_video and create_music_video with its plan_id. It also states the important condition that this happens before anything is charged.

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