Skip to main content
Glama

Quote a music video

quote_music_video
Read-onlyIdempotent

The exact credits for an AI music video, before anything is charged Returns quote_id, credits and a breakdown; the price follows the section's length (clips of about 15 seconds). The song's artist performs it, so the artist needs their character (start_character). With a plan_id, test: true prices testing the plan first (its chorus's shots at 480p; test in the answer says which shots and seconds): offer it beside the whole video's quote. Always quote first and tell the user the credits before creating; credits are reserved at creation and charged only when the video is delivered.

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": "quote_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
testNoWith plan_id: test the plan before the whole video. Only its test shots are made (the first chorus, else the sung section with the most lead words; whole shots, about 20 seconds at most), at 480p whatever quality is sent, with the plan's seeds and pictures, for a fraction of the price. The quote and get_video say which shots and seconds (test). It is an ordinary video marked as a test: no outro, one variation, never revised. Then order the whole video from the same plan_id without test
trimNoPerform only this section of the song (15 seconds to 10 minutes); omitted, the whole song (15 seconds to 10 minutes long). The price follows its length. 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
outroNoOptional: end on a release card after the last shot, the song playing on under it (the delivered video is up to 5 seconds longer; the director designs it for the video, or look_id: a lyric video Look from list_looks whose card is used as it is). display: title, artist, cover, badges (true/false) and optional cover_scale, text_scale, artist_scale, spacing_scale. Free with the video
styleNoOptional visual style, how it is rendered: natural, film, golden-hour, neon-night, noir, vintage, dreamy, super-8, vhs, documentary, glossy-pop, indie, cyberpunk, y2k, lofi, painterly, anime or clay (get_options lists the ones each model makes). Omit it and 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
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)
plan_idNoMake the video from this plan (plan_music_video): its brief (model, kind, visual style, format, section…) replaces the one sent, so send song_id and plan_id; quality left out is the plan's model's default. Omitted, the director plans it while it is made
qualityNoThe resolution it is made at: one of the qualities get_options lists for the model (left out, the model's default_quality: 768p for MiniMax H3 Max, 720p for Seedance; a sharper one is the same video for more credits); not part of the plan, so a plan is made in any quality. get_options lists each model's qualities with about how long each takes; credits.music_video.models has a minute by model and quality
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: sings to camera in one place), intercut (performance cut against the artist living the song's story), cinematic (a moving camera through a location), story (acts out the song's story) or surreal (the world transforms with the song). get_options lists the ones each model makesperformance
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
metadataNoYour own JSON (an order id, for example): kept with the video and returned in its request. Quote and create with the same value
refinishNoFinish a delivered music video again with another outro, or none (send song_id, refinish.video_id and outro or not; one variation): no shot is made again (its kept shots are joined again under the song), only setup and delivery are charged. Needs the video's revisable_until ahead
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).
casting_idNoOrdered without a plan: a casting (cast_music_video) the user said yes to in full. Its people still proposed are drawn inside the order (the quote's "New cast" line, at the character sheet price each; only those drawn are charged), kept in the song artist's kit as AI-made and added to people. Not with plan_id or cast_mode exact
variationsNo1–4 different music videos
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_ratioNoThe one format of the file: "9:16" (default, vertical), "16:9" (wide) or "1:1" (square)9:16
callback_urlNoAn https URL to POST the finished video to (signed; see Callbacks). Quote and create with the same value
design_shootNoWithout a plan: the director first designs the shoot (the outfits, places and props the brief leaves open) and draws each as a picture every shot is given. The quote counts the most pictures it may draw; only those drawn are charged

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 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"
      +}
    • addedInput schema / properties / casting_id
      Added value: +{
      +  "description": "Ordered without a plan: a casting (cast_music_video) the user said yes to in full. Its people still proposed are drawn inside the order (the quote's \"New cast\" line, at the character sheet price each; only those drawn are charged), kept in the song artist's kit as AI-made and added to people. Not with plan_id or cast_mode exact",
      +  "pattern": "^casting_[0-9a-f-]{36}$",
      +  "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"
      +}
    • addedInput schema / properties / test
      Added value: +{
      +  "description": "With plan_id: test the plan before the whole video. Only its test shots are made (the first chorus, else the sung section with the most lead words; whole shots, about 20 seconds at most), at 480p whatever quality is sent, with the plan's seeds and pictures, for a fraction of the price. The quote and get_video say which shots and seconds (test). It is an ordinary video marked as a test: no outro, one variation, never revised. Then order the whole video from the same plan_id without test",
      +  "type": "boolean"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / plan_id / description
      Previous value: -"Make the video from this plan (plan_music_video): its brief (model, kind, look, format, section…) replaces the one sent, so send song_id and plan_id; quality left out is the plan's model's default. Omitted, the director plans it while it is made"New value: +"Make the video from this plan (plan_music_video): its brief (model, kind, visual style, format, section…) replaces the one sent, so send song_id and plan_id; quality left out is the plan's model's default. Omitted, the director plans it while it is made"
    • changedInput schema / properties / style / description
      Previous value: -"Optional look: natural, film, golden-hour, neon-night, noir, vintage or dreamy. Omit it and the director picks one from the cover"New value: +"Optional visual style, how it is rendered: natural, film, golden-hour, neon-night, noir, vintage, dreamy, super-8, vhs, documentary, glossy-pop, indie, cyberpunk, y2k, lofi, painterly, anime or clay (get_options lists the ones each model makes). Omit it and the director picks one from the cover"
  3. Changed1 schema field changed
    • changedInput schema / properties / refinish / description
      Previous value: -"Finish a delivered music video again with another outro, or none (send song_id, refinish.video_id and outro or not; one variation): no shot is made again, only setup and delivery are charged. Needs the video's revisable_until ahead"New value: +"Finish a delivered music video again with another outro, or none (send song_id, refinish.video_id and outro or not; one variation): no shot is made again (its kept shots are joined again under the song), only setup and delivery are charged. Needs the video's revisable_until ahead"
  4. Changed2 schema fields 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"
    • changedInput schema / properties / plan_id / description
      Previous value: -"Make the video from this plan (plan_music_video): its brief replaces the one sent, so send song_id and plan_id. Omitted, the director plans it while it is made"New value: +"Make the video from this plan (plan_music_video): its brief (model, kind, look, format, section…) replaces the one sent, so send song_id and plan_id; quality left out is the plan's model's default. Omitted, the director plans it while it is made"
  5. 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"
  6. 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)."
  7. Changed21 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"
      +]
    • addedInput schema / properties / design_shoot
      Added value: +{
      +  "default": false,
      +  "description": "Without a plan: the director first designs the shoot (the outfits, places and props the brief leaves open) and draws each as a picture every shot is given. The quote counts the most pictures it may draw; only those drawn are charged",
      +  "type": "boolean"
      +}
    • 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 / outro
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Optional: end on a release card after the last shot, the song playing on under it (the delivered video is up to 5 seconds longer; the director designs it for the video, or look_id: a lyric video Look from list_looks whose card is used as it is). display: title, artist, cover, badges (true/false) and optional cover_scale, text_scale, artist_scale, spacing_scale. Free with the video",
      +  "properties": {
      +    "display": {
      +      "additionalProperties": false,
      +      "properties": {
      +        "artist": {
      +          "default": true,
      +          "type": "boolean"
      +        },
      +        "artist_scale": {
      +          "maximum": 1.5,
      +          "minimum": 0.85,
      +          "type": "number"
      +        },
      +        "badges": {
      +          "default": true,
      +          "type": "boolean"
      +        },
      +        "cover": {
      +          "default": true,
      +          "type": "boolean"
      +        },
      +        "cover_scale": {
      +          "maximum": 1.25,
      +          "minimum": 0.75,
      +          "type": "number"
      +        },
      +        "spacing_scale": {
      +          "maximum": 1.5,
      +          "minimum": 0.75,
      +          "type": "number"
      +        },
      +        "text_scale": {
      +          "maximum": 1.3,
      +          "minimum": 0.85,
      +          "type": "number"
      +        },
      +        "title": {
      +          "default": true,
      +          "type": "boolean"
      +        }
      +      },
      +      "type": "object"
      +    },
      +    "look_id": {
      +      "maxLength": 120,
      +      "minLength": 1,
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "display"
      +  ],
      +  "type": "object"
      +}
    • 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"
      +}
    • removedInput schema / properties / quality / default
      Removed value: -"768p"
    • changedInput schema / properties / quality / description
      Previous value: -"The resolution it is made at: one of the qualities get_options lists for the model (768p by default; 1080p is the same video sharper for about twice the credits); not part of the plan, so a plan is made in any quality. get_options lists each model's qualities with about how long each takes; credits.music_video.models has a minute by model and quality"New value: +"The resolution it is made at: one of the qualities get_options lists for the model (left out, the model's default_quality: 768p for MiniMax H3 Max, 720p for Seedance; a sharper one is the same video for more credits); not part of the plan, so a plan is made in any quality. get_options lists each model's qualities with about how long each takes; credits.music_video.models has a minute by model and quality"
    • changedInput schema / properties / quality / enum
      Previous value: -[
      -  "480p",
      -  "768p",
      -  "1080p"
      -]New value: +[
      +  "480p",
      +  "720p",
      +  "768p",
      +  "1080p",
      +  "4k"
      +]
    • addedInput schema / properties / refinish
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Finish a delivered music video again with another outro, or none (send song_id, refinish.video_id and outro or not; one variation): no shot is made again, only setup and delivery are charged. Needs the video's revisable_until ahead",
      +  "properties": {
      +    "video_id": {
      +      "format": "uuid",
      +      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "video_id"
      +  ],
      +  "type": "object"
      +}
    • 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)"
  8. Changed3 schema fields changed
    • changedInput schema / properties / category / description
      Previous value: -"performance (default: sings to camera in one place), intercut (performance cut against the artist living the song's story), cinematic (a moving camera through a location), story (acts out the song's story in one take) or surreal (the world transforms with the song). get_options lists the ones each model makes"New value: +"performance (default: sings to camera in one place), intercut (performance cut against the artist living the song's story), cinematic (a moving camera through a location), story (acts out the song's story) or surreal (the world transforms with the song). get_options lists the ones each model makes"
    • 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"
      +}
  9. Changed1 schema field changed
    • changedInput schema / properties / trim / description
      Previous value: -"Perform only this section of the song (15 seconds to 10 minutes); omitted, the whole song (15 seconds to 10 minutes long). The price follows its length"New value: +"Perform only this section of the song (15 seconds to 10 minutes); omitted, the whole song (15 seconds to 10 minutes long). The price follows its length. Best: a part from get_song_analysis (parts[]: its start and end never cut a word)"
  10. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real billing semantics beyond that: credits are reserved at creation and charged only on delivery, price scales with the trimmed section length, and a test quote is 480p at a fraction of the price. It stops short of saying how long a quote_id stays valid or whether re-quoting the same input yields the same figure.

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?

Front-loaded with purpose and pricing, and every sentence carries information about cost or workflow. It loses a point for a broken sentence boundary ("before anything is charged Returns quote_id") and for re-explaining test-at-480p detail that already lives in the schema.

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 28-parameter tool with no output schema, the description supplies the essentials an agent needs: what comes back, how price is determined, and the quote-before-create rule. The remaining gap is quote lifetime/reuse, which matters given the idempotent hint but is never addressed.

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?

With 96% schema coverage the schema carries the parameter burden, yet the description still adds meaning: the trim section drives price via ~15-second clips, plan_id plus test produces a reduced trial quote, and song_id implies the artist's character requirement. It reinforces rather than merely restates the schema.

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 ("The exact credits for an AI music video") and immediately names the return payload (quote_id, credits, breakdown). It also separates itself from the downstream create step ("Always quote first ... before creating") and names the prerequisite sibling start_character, so an agent can place it in the workflow without opening the schema.

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?

Gives explicit sequencing ("Always quote first and tell the user the credits before creating") and a conditional alternative: with a plan_id, also price the test run and "offer it beside the whole video's quote." When-not guidance is implied by the creation boundary and the artist-character prerequisite is stated.

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