Skip to main content
Glama

kelpo_update_editing_plan

Save an external assistant's structured edit plan without invoking a planner or rendering. Only selected job_ids are allowed; clip start/end are source seconds, speed x0.25–x4; every finishing touch (texts, overlays, subtitles items, zooms) uses FINAL montage seconds. Send the complete plan: omitted finishing touches are removed. Show the full recap and request explicit approval before render_editing. Preserve prior clips except requested changes. Arguments: {"path": {"id": ""}, "body": {"version": 3, "plan": ""}}

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": {
      "path": "<path>",
      "body": "<body>"
    },
    "name": "kelpo_update_editing_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes
pathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / $defs / Subtitles / properties / style / description
      Previous value: -"shorts (default): one text at a time, bold capitals, keywords in a light colour, a dark brand-coloured box following the spoken word; the hooks show alone before the speech and their *accents* become keywords. classic: white outlined lines, hooks shown separately. word (SUBTITLE_STYLES): ONE big lowercase word at a time, on the voice, keywords in yellow or blue (picked from the video). bold (SUBTITLE_STYLES): two or three big capital words at a time, keywords in yellow or blue, light shadow, no box."New value: +"shorts (default): one text at a time, bold capitals, keywords in a light colour, a dark brand-coloured box following the spoken word; the hooks show alone before the speech and their *accents* become keywords. classic: white outlined lines, hooks shown separately. word (SUBTITLE_STYLES): ONE big lowercase word at a time, on the voice, keywords in yellow or blue (picked from the video). bold (SUBTITLE_STYLES): two or three big capital words at a time, keywords in yellow or blue, light shadow, no box. stack (SUBTITLE_STYLES): phone-Reel look at the top of the picture, the words of each sentence appear one by one and stay stacked in short capital lines of equal width, the spoken word in a glowing violet (or brand) box, keywords in yellow; a short opening phrase (e.g. \"Rappel sympathique,\") stays small above the first sentence."
    • changedInput schema / $defs / Subtitles / properties / style / enum
      Previous value: -[
      -  "shorts",
      -  "classic",
      -  "word",
      -  "bold"
      -]New value: +[
      +  "shorts",
      +  "classic",
      +  "word",
      +  "bold",
      +  "stack"
      +]
  2. Changed6 schema fields changed
    • addedInput schema / $defs / Card
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Floating card in front of the person (MONTAGE_CHAPTERS): one image in a big rounded portrait card, or two images\nas its two halves (a comparison), zooming up on the spoken words, with white bold captions on the images.",
      +  "properties": {
      +    "asset_ids": {
      +      "description": "One image (an example, a post, a screenshot, a profile) or two (top and bottom halves of the card, a comparison). The person's own uploaded images, never generated.",
      +      "items": {
      +        "type": "string"
      +      },
      +      "maxItems": 2,
      +      "minItems": 1,
      +      "title": "Asset Ids",
      +      "type": "array"
      +    },
      +    "at_words": {
      +      "default": "",
      +      "description": "Spoken words on which the card pops in (copied as said). Or give start.",
      +      "maxLength": 80,
      +      "title": "At Words",
      +      "type": "string"
      +    },
      +    "caption_position": {
      +      "default": "center",
      +      "description": "Caption in the middle of each image, or at its top (\"before:\").",
      +      "enum": [
      +        "center",
      +        "top"
      +      ],
      +      "title": "Caption Position",
      +      "type": "string"
      +    },
      +    "captions": {
      +      "description": "Optional white bold caption on each image (max 40 each), video language, e.g. [\"be ambitious\", \"enjoy a slow morning\"] or [\"before:\"].",
      +      "items": {
      +        "type": "string"
      +      },
      +      "maxItems": 2,
      +      "title": "Captions",
      +      "type": "array"
      +    },
      +    "end": {
      +      "anyOf": [
      +        {
      +          "exclusiveMinimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Or: end in FINAL montage seconds.",
      +      "title": "End"
      +    },
      +    "fit": {
      +      "default": "auto",
      +      "description": "auto = fills the portrait card, a wide image (profile screenshot) shown whole; cover; whole.",
      +      "enum": [
      +        "auto",
      +        "cover",
      +        "whole"
      +      ],
      +      "title": "Fit",
      +      "type": "string"
      +    },
      +    "position": {
      +      "default": "center",
      +      "description": "Height of the card: center (default, over the body, the face stays visible), upper, lower.",
      +      "enum": [
      +        "center",
      +        "upper",
      +        "lower"
      +      ],
      +      "title": "Position",
      +      "type": "string"
      +    },
      +    "start": {
      +      "anyOf": [
      +        {
      +          "minimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Or: start in FINAL montage seconds.",
      +      "title": "Start"
      +    },
      +    "until_words": {
      +      "default": "",
      +      "description": "Optional: spoken words after which it goes (else: the next card, or about 2.6 s).",
      +      "maxLength": 80,
      +      "title": "Until Words",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "asset_ids"
      +  ],
      +  "title": "Card",
      +  "type": "object"
      +}
    • addedInput schema / $defs / Chapter
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Numbered chapter of a talking video (MONTAGE_CHAPTERS, editing_chapters.py): a full-screen paper card (a brush-pen\nnumber drawn on, the title typed in tight bold letters) brought in by a transition, then the title kept at the top of\nthe picture until the next chapter. card=false = a title only over the face (the hook « 3 trends du moment »).",
      +  "properties": {
      +    "accent": {
      +      "default": "",
      +      "description": "Number colour on the paper. Empty = periwinkle.",
      +      "pattern": "^(#[0-9a-fA-F]{6})?$",
      +      "title": "Accent",
      +      "type": "string"
      +    },
      +    "at_words": {
      +      "default": "",
      +      "description": "Spoken words that open the chapter (copied exactly as said, e.g. \"le premier\"): the card covers the picture just as they are said. Or give start.",
      +      "maxLength": 80,
      +      "title": "At Words",
      +      "type": "string"
      +    },
      +    "background": {
      +      "default": "",
      +      "description": "Paper colour #rrggbb. Empty = pink-beige paper.",
      +      "pattern": "^(#[0-9a-fA-F]{6})?$",
      +      "title": "Background",
      +      "type": "string"
      +    },
      +    "card": {
      +      "default": true,
      +      "description": "true = full-screen paper card (the voice runs on under it); false = title only over the face (a hook).",
      +      "title": "Card",
      +      "type": "boolean"
      +    },
      +    "card_end": {
      +      "anyOf": [
      +        {
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Server-computed; leave empty.",
      +      "title": "Card End"
      +    },
      +    "card_seconds": {
      +      "default": 1.5,
      +      "description": "How long the card stays (at least the time to type the title).",
      +      "maximum": 3,
      +      "minimum": 0.8,
      +      "title": "Card Seconds",
      +      "type": "number"
      +    },
      +    "card_start": {
      +      "anyOf": [
      +        {
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Server-computed; leave empty.",
      +      "title": "Card Start"
      +    },
      +    "end": {
      +      "anyOf": [
      +        {
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Server-computed; leave empty.",
      +      "title": "End"
      +    },
      +    "ink": {
      +      "default": "",
      +      "description": "Title colour on the paper. Empty = deep indigo.",
      +      "pattern": "^(#[0-9a-fA-F]{6})?$",
      +      "title": "Ink",
      +      "type": "string"
      +    },
      +    "keep_title": {
      +      "default": true,
      +      "description": "true = after the card, the number and title stay at the top of the picture until the next chapter, then are erased.",
      +      "title": "Keep Title",
      +      "type": "boolean"
      +    },
      +    "number": {
      +      "default": "",
      +      "description": "Big number of the chapter, e.g. \"1\" (empty = none). For the hook of a list video: the count, e.g. \"3\".",
      +      "maxLength": 3,
      +      "pattern": "^[0-9A-Za-z]{0,3}$",
      +      "title": "Number",
      +      "type": "string"
      +    },
      +    "number_color": {
      +      "default": "",
      +      "description": "Number colour over the picture. Empty = white (kept title) or cream (hook).",
      +      "pattern": "^(#[0-9a-fA-F]{6})?$",
      +      "title": "Number Color",
      +      "type": "string"
      +    },
      +    "sound": {
      +      "default": true,
      +      "description": "Soft swoosh with the cloth / paper transition.",
      +      "title": "Sound",
      +      "type": "boolean"
      +    },
      +    "start": {
      +      "anyOf": [
      +        {
      +          "minimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Or: start in FINAL montage seconds. Omit with at_words.",
      +      "title": "Start"
      +    },
      +    "subtitle": {
      +      "default": "",
      +      "description": "Optional short line in handwriting under the title, e.g. \"novembre\" (a hook).",
      +      "maxLength": 24,
      +      "title": "Subtitle",
      +      "type": "string"
      +    },
      +    "title": {
      +      "description": "Title in the video language, lowercase like a Reel, e.g. \"le bouton on / off\" (max 48); split in two balanced lines by the server, | forces the break (\"le bouton|on / off\").",
      +      "maxLength": 48,
      +      "minLength": 1,
      +      "title": "Title",
      +      "type": "string"
      +    },
      +    "title_color": {
      +      "default": "",
      +      "description": "Title colour over the picture. Empty = pale yellow (kept title) or white (hook).",
      +      "pattern": "^(#[0-9a-fA-F]{6})?$",
      +      "title": "Title Color",
      +      "type": "string"
      +    },
      +    "title_end": {
      +      "anyOf": [
      +        {
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Server-computed; leave empty.",
      +      "title": "Title End"
      +    },
      +    "title_position": {
      +      "default": "auto",
      +      "description": "card false: auto = over the middle of the picture (a hook), top = at the top.",
      +      "enum": [
      +        "auto",
      +        "top"
      +      ],
      +      "title": "Title Position",
      +      "type": "string"
      +    },
      +    "title_size": {
      +      "default": "auto",
      +      "description": "Kept title size: auto (small, at the top) or large.",
      +      "enum": [
      +        "auto",
      +        "large"
      +      ],
      +      "title": "Title Size",
      +      "type": "string"
      +    },
      +    "title_start": {
      +      "anyOf": [
      +        {
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Server-computed; leave empty.",
      +      "title": "Title Start"
      +    },
      +    "transition": {
      +      "default": "cloth",
      +      "description": "cloth = a crumpled white sheet thrown at the camera covers the picture, cut to the paper (soft swoosh); paper = the card slides up; cut = straight cut.",
      +      "enum": [
      +        "cloth",
      +        "paper",
      +        "cut"
      +      ],
      +      "title": "Transition",
      +      "type": "string"
      +    },
      +    "until_words": {
      +      "default": "",
      +      "description": "Optional: spoken words after which the kept title is erased (else: the next chapter or the end). Use it so the call to action is the face alone.",
      +      "maxLength": 80,
      +      "title": "Until Words",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "title"
      +  ],
      +  "title": "Chapter",
      +  "type": "object"
      +}
    • addedInput schema / $defs / Flash
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Warm light leak over the picture (MONTAGE_CHAPTERS), e.g. just before the call to action.",
      +  "properties": {
      +    "at_words": {
      +      "default": "",
      +      "description": "Spoken words it flashes on (copied as said). Or give start.",
      +      "maxLength": 80,
      +      "title": "At Words",
      +      "type": "string"
      +    },
      +    "color": {
      +      "default": "",
      +      "description": "Light colour #rrggbb. Empty = warm orange.",
      +      "pattern": "^(#[0-9a-fA-F]{6})?$",
      +      "title": "Color",
      +      "type": "string"
      +    },
      +    "side": {
      +      "default": "right",
      +      "enum": [
      +        "right",
      +        "left"
      +      ],
      +      "title": "Side",
      +      "type": "string"
      +    },
      +    "start": {
      +      "anyOf": [
      +        {
      +          "minimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Or: start in FINAL montage seconds.",
      +      "title": "Start"
      +    }
      +  },
      +  "title": "Flash",
      +  "type": "object"
      +}
    • addedInput schema / $defs / Plan / properties / cards
      Added value: +{
      +  "description": "Optional floating cards in front of the person (MONTAGE_CHAPTERS): one image in a big rounded card, or two as its halves with captions, zooming up on spoken words. For the person's examples, posts, screenshots, comparisons.",
      +  "items": {
      +    "$ref": "#/$defs/Card"
      +  },
      +  "maxItems": 16,
      +  "title": "Cards",
      +  "type": "array"
      +}
    • addedInput schema / $defs / Plan / properties / chapters
      Added value: +{
      +  "description": "Optional numbered chapters of a talking video (MONTAGE_CHAPTERS: a list video « 3 tips », « 3 trends »): full-screen paper card, number drawn on, title typed, after a cloth or paper transition, then the title kept at the top until the next chapter. card false = a title over the face (the hook, instead of texts). Recipe « List video in chapters » in kelpo_video_recipe.",
      +  "items": {
      +    "$ref": "#/$defs/Chapter"
      +  },
      +  "maxItems": 8,
      +  "title": "Chapters",
      +  "type": "array"
      +}
    • addedInput schema / $defs / Plan / properties / flashes
      Added value: +{
      +  "description": "Optional warm light leaks (MONTAGE_CHAPTERS), e.g. on the first words of the call to action.",
      +  "items": {
      +    "$ref": "#/$defs/Flash"
      +  },
      +  "maxItems": 4,
      +  "title": "Flashes",
      +  "type": "array"
      +}
  3. Changed7 schema fields changed
    • addedInput schema / $defs / Box
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "A rectangle of the picture, in fractions of its width and height (0 = left / top edge).",
      +  "properties": {
      +    "h": {
      +      "exclusiveMinimum": 0,
      +      "maximum": 1,
      +      "title": "H",
      +      "type": "number"
      +    },
      +    "w": {
      +      "exclusiveMinimum": 0,
      +      "maximum": 1,
      +      "title": "W",
      +      "type": "number"
      +    },
      +    "x": {
      +      "maximum": 1,
      +      "minimum": 0,
      +      "title": "X",
      +      "type": "number"
      +    },
      +    "y": {
      +      "maximum": 1,
      +      "minimum": 0,
      +      "title": "Y",
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "x",
      +    "y",
      +    "w",
      +    "h"
      +  ],
      +  "title": "Box",
      +  "type": "object"
      +}
    • addedInput schema / $defs / Bumper
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Full-screen broadcast card with its sound (« BREAKING NEWS » sting) laid over a cut between two passages: it covers\nthe end of the passage before the cut (or straddles it), the montage's own sound is lowered under it. Leave a silent tail\nof at least `seconds` on the passage before (a movie scene: a few seconds more than its lines).",
      +  "properties": {
      +    "align": {
      +      "default": "before_cut",
      +      "description": "before_cut (default) = ends exactly on the cut; center = straddles it.",
      +      "enum": [
      +        "before_cut",
      +        "center"
      +      ],
      +      "title": "Align",
      +      "type": "string"
      +    },
      +    "at_cut": {
      +      "anyOf": [
      +        {
      +          "maximum": 11,
      +          "minimum": 1,
      +          "type": "integer"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "The cut after passage N (1 = between the first and second clip).",
      +      "title": "At Cut"
      +    },
      +    "color": {
      +      "default": "",
      +      "description": "Band colour #rrggbb. Empty = news red.",
      +      "pattern": "^(#[0-9a-fA-F]{6})?$",
      +      "title": "Color",
      +      "type": "string"
      +    },
      +    "seconds": {
      +      "default": 1.4,
      +      "maximum": 3,
      +      "minimum": 0.6,
      +      "title": "Seconds",
      +      "type": "number"
      +    },
      +    "sound": {
      +      "default": "alert",
      +      "description": "alert = news jingle, whoosh = a short swoosh, none.",
      +      "enum": [
      +        "alert",
      +        "whoosh",
      +        "none"
      +      ],
      +      "title": "Sound",
      +      "type": "string"
      +    },
      +    "start": {
      +      "anyOf": [
      +        {
      +          "minimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Or an explicit start, FINAL montage seconds.",
      +      "title": "Start"
      +    },
      +    "subtext": {
      +      "default": "",
      +      "description": "Small line under it, e.g. \"LIVE\".",
      +      "maxLength": 24,
      +      "title": "Subtext",
      +      "type": "string"
      +    },
      +    "text": {
      +      "description": "Big words, e.g. \"BREAKING NEWS\", \"MEANWHILE\", \"SPECIAL REPORT\" (capitals, one or two lines).",
      +      "maxLength": 24,
      +      "minLength": 1,
      +      "title": "Text",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "text"
      +  ],
      +  "title": "Bumper",
      +  "type": "object"
      +}
    • addedInput schema / $defs / Inset
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "An image shown INSIDE a part of the picture (05/11, JT sketch): the screen of a set, a TV on a wall, a phone, or a\nsmall picture in a corner. green = replaces the chroma-green area of the shot (found by the server; people in front of\nit stay in front, and when the camera cuts away from the green the image disappears by itself); box = a plain\nrectangle at `box` (e.g. a corner picture), with an optional white border.",
      +  "properties": {
      +    "asset_id": {
      +      "maxLength": 32,
      +      "minLength": 32,
      +      "pattern": "^[a-f0-9]{32}$",
      +      "title": "Asset Id",
      +      "type": "string"
      +    },
      +    "at_words": {
      +      "default": "",
      +      "description": "Spoken words on which the image appears (copied as said), e.g. the reveal word.",
      +      "maxLength": 80,
      +      "title": "At Words",
      +      "type": "string"
      +    },
      +    "border": {
      +      "default": false,
      +      "description": "mode box: a thin white border.",
      +      "title": "Border",
      +      "type": "boolean"
      +    },
      +    "box": {
      +      "anyOf": [
      +        {
      +          "$ref": "#/$defs/Box"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "mode box: where, in fractions of the picture, e.g. {\"x\":0.62,\"y\":0.05,\"w\":0.33,\"h\":0.2} for the top right corner. mode green: optional, limits the search for the green area."
      +    },
      +    "clip": {
      +      "anyOf": [
      +        {
      +          "maximum": 12,
      +          "minimum": 1,
      +          "type": "integer"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Optional: only during this passage (1 = first clip); default times = the whole passage.",
      +      "title": "Clip"
      +    },
      +    "end": {
      +      "anyOf": [
      +        {
      +          "exclusiveMinimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "End, FINAL montage seconds. Omit: until until_words, the next inset of the same mode, the end of its clip or of the montage.",
      +      "title": "End"
      +    },
      +    "fit": {
      +      "default": "cover",
      +      "description": "cover = fills the area (edges cut); contain = the whole image, on dark blue.",
      +      "enum": [
      +        "cover",
      +        "contain"
      +      ],
      +      "title": "Fit",
      +      "type": "string"
      +    },
      +    "mode": {
      +      "default": "green",
      +      "description": "green = in the chroma-green screen of the shot (generate the set with a plain bright green screen); box = a rectangle at box.",
      +      "enum": [
      +        "green",
      +        "box"
      +      ],
      +      "title": "Mode",
      +      "type": "string"
      +    },
      +    "start": {
      +      "anyOf": [
      +        {
      +          "minimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Start, FINAL montage seconds. Omit with at_words or clip.",
      +      "title": "Start"
      +    },
      +    "until_words": {
      +      "default": "",
      +      "description": "Optional: spoken words after which it disappears.",
      +      "maxLength": 80,
      +      "title": "Until Words",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "asset_id"
      +  ],
      +  "title": "Inset",
      +  "type": "object"
      +}
    • addedInput schema / $defs / LowerThird
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "News lower third (bandeau): a small coloured tag, a big title line, a thin sub line, an optional clock. Several of\nthem follow one another (each until the next one or its until_words).",
      +  "properties": {
      +    "at_words": {
      +      "default": "",
      +      "description": "Spoken words on which it appears (copied as said).",
      +      "maxLength": 80,
      +      "title": "At Words",
      +      "type": "string"
      +    },
      +    "clip": {
      +      "anyOf": [
      +        {
      +          "maximum": 12,
      +          "minimum": 1,
      +          "type": "integer"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Optional: only during this passage.",
      +      "title": "Clip"
      +    },
      +    "clock": {
      +      "default": "",
      +      "description": "Optional clock on the right of the tag, e.g. \"6:41 PM\" (a later clock after a cut tells time has passed).",
      +      "maxLength": 10,
      +      "title": "Clock",
      +      "type": "string"
      +    },
      +    "color": {
      +      "default": "",
      +      "description": "Tag and edge colour #rrggbb. Empty = news red.",
      +      "pattern": "^(#[0-9a-fA-F]{6})?$",
      +      "title": "Color",
      +      "type": "string"
      +    },
      +    "end": {
      +      "anyOf": [
      +        {
      +          "exclusiveMinimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "title": "End"
      +    },
      +    "start": {
      +      "anyOf": [
      +        {
      +          "minimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "title": "Start"
      +    },
      +    "subtitle": {
      +      "default": "",
      +      "description": "Thin line under the title, e.g. \"HAVE YOU SEEN BISCUIT? CALL 555-0142\".",
      +      "maxLength": 56,
      +      "title": "Subtitle",
      +      "type": "string"
      +    },
      +    "tag": {
      +      "default": "",
      +      "description": "Small coloured tag above, e.g. \"BREAKING NEWS\", \"LIVE\", \"LOCAL NEWS\".",
      +      "maxLength": 20,
      +      "title": "Tag",
      +      "type": "string"
      +    },
      +    "title": {
      +      "description": "Big line, e.g. \"FAMILY SEARCHING FOR LOST DOG\" (shown in capitals).",
      +      "maxLength": 40,
      +      "minLength": 1,
      +      "title": "Title",
      +      "type": "string"
      +    },
      +    "until_words": {
      +      "default": "",
      +      "maxLength": 80,
      +      "title": "Until Words",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "title"
      +  ],
      +  "title": "LowerThird",
      +  "type": "object"
      +}
    • addedInput schema / $defs / Plan / properties / bumpers
      Added value: +{
      +  "description": "Optional full-screen broadcast cards with their sound over a cut (\"BREAKING NEWS\"), to mark that time has passed between two passages.",
      +  "items": {
      +    "$ref": "#/$defs/Bumper"
      +  },
      +  "maxItems": 4,
      +  "title": "Bumpers",
      +  "type": "array"
      +}
    • addedInput schema / $defs / Plan / properties / insets
      Added value: +{
      +  "description": "Optional images shown INSIDE part of the picture: the green screen of a set (mode green: the image changes on spoken words, people in front stay in front) or a small framed corner picture (mode box).",
      +  "items": {
      +    "$ref": "#/$defs/Inset"
      +  },
      +  "maxItems": 12,
      +  "title": "Insets",
      +  "type": "array"
      +}
    • addedInput schema / $defs / Plan / properties / lower_thirds
      Added value: +{
      +  "description": "Optional news lower thirds (tag, title, sub line, clock), each until the next one; on spoken words or per passage.",
      +  "items": {
      +    "$ref": "#/$defs/LowerThird"
      +  },
      +  "maxItems": 8,
      +  "title": "Lower Thirds",
      +  "type": "array"
      +}
  4. Changed2 schema fields changed
    • addedInput schema / $defs / Footer
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Fixed link line (editing_footer.py, owner 2026-11-04): the person's own link (e.g. monsite.com/promo) shown for the\nwhole video, bold, centred, with an optional small grey caption above it. Under the picture in a vertical frame, else in\nthe zone the TikTok / Reels / Shorts buttons and captions leave free. Never a Kelpo mark: only the person's text.",
      +  "properties": {
      +    "accent": {
      +      "default": "",
      +      "description": "Colour #rrggbb of the *accented* part. Empty = the title accent colour (cyan by default).",
      +      "pattern": "^(#[0-9a-fA-F]{6})?$",
      +      "title": "Accent",
      +      "type": "string"
      +    },
      +    "caption": {
      +      "default": "",
      +      "description": "Optional small grey line above the link (max 40, video language), e.g. \"Make your own AI character\". Empty = link alone.",
      +      "maxLength": 40,
      +      "title": "Caption",
      +      "type": "string"
      +    },
      +    "link": {
      +      "description": "The link or short address shown in bold for the whole video (max 40 characters without the *), e.g. \"monsite.com/*promo*\"; *word* = accent colour (like the title). Copied from the person, never invented.",
      +      "maxLength": 48,
      +      "minLength": 1,
      +      "title": "Link",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "link"
      +  ],
      +  "title": "Footer",
      +  "type": "object"
      +}
    • addedInput schema / $defs / Plan / properties / footer
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/Footer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Optional fixed link line for the whole video: the person's link in bold (e.g. \"monsite.com/*promo*\"), optional small caption above. Placed by the server under the picture in a vertical frame, else above the TikTok / Reels / Shorts captions and away from the right-hand buttons; subtitles move up to stay clear of it."
      +}
  5. Changed7 schema fields changed
    • addedInput schema / $defs / Clip / properties / pace
      Added value: +{
      +  "default": true,
      +  "description": "With a vertical frame whose pace is above 1: false = this passage stays at its own speed (x1), e.g. a street shot where passers-by would look sped up.",
      +  "title": "Pace",
      +  "type": "boolean"
      +}
    • addedInput schema / $defs / Frame
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Vertical frame (MONTAGE_FRAME): a 16:9 montage shown in a 9:16 video for TikTok / Reels / Shorts, at its native size\n(never reduced or enlarged), on a plain background, with a fixed title above it for the whole video.",
      +  "properties": {
      +    "accents": {
      +      "description": "Colours #rrggbb of the accented words, in turn (e.g. [\"#2ed6f2\"] cyan, [\"#ffe14d\",\"#ff5c8a\"]). Empty = cyan.",
      +      "items": {
      +        "type": "string"
      +      },
      +      "maxItems": 4,
      +      "title": "Accents",
      +      "type": "array"
      +    },
      +    "color": {
      +      "default": "#000000",
      +      "description": "Background of the frame #rrggbb (default black).",
      +      "pattern": "^#[0-9a-fA-F]{6}$",
      +      "title": "Color",
      +      "type": "string"
      +    },
      +    "grain": {
      +      "default": "none",
      +      "description": "Period look on the picture only (title and subtitles stay sharp), always subtle (no blur): light70 / light80 = a little grain, warm 70s or vivid 80s (recommended when a look is wanted); film70 = 70s film colours; vhs80 = 80s VHS colours and faint scan lines; bw60 = black and white 60s; broadcast90 = early 90s TV. none (default).",
      +      "enum": [
      +        "none",
      +        "light70",
      +        "light80",
      +        "film70",
      +        "vhs80",
      +        "bw60",
      +        "broadcast90"
      +      ],
      +      "title": "Grain",
      +      "type": "string"
      +    },
      +    "pace": {
      +      "default": 1,
      +      "description": "Speech pace of every passage at normal speed: 1 (default), 1.1 or 1.2 (a bit livelier, same voice pitch). The duration shrinks accordingly. Keep 1 for a shot where other people are visible (street, passers-by, crowd: sped up they look fake), or set that clip's pace false.",
      +      "maximum": 1.3,
      +      "minimum": 1,
      +      "title": "Pace",
      +      "type": "number"
      +    },
      +    "title": {
      +      "default": "",
      +      "description": "Fixed title above the picture for the whole video (max 120, in the video's language), e.g. \"Why I always give **three prices**\". **words** (or *words*) = accent colour; several accented groups take the accents colours in turn. Empty = no title.",
      +      "maxLength": 120,
      +      "title": "Title",
      +      "type": "string"
      +    },
      +    "title_case": {
      +      "default": "as_written",
      +      "enum": [
      +        "as_written",
      +        "upper"
      +      ],
      +      "title": "Title Case",
      +      "type": "string"
      +    },
      +    "title_color": {
      +      "default": "",
      +      "description": "Title colour #rrggbb. Empty = white (black on a light frame).",
      +      "pattern": "^(#[0-9a-fA-F]{6})?$",
      +      "title": "Title Color",
      +      "type": "string"
      +    },
      +    "title_font": {
      +      "default": "classic",
      +      "description": "classic (bold sans, the usual Shorts title), modern (rounded geometric), serif (elegant, old-money), typewriter (archive, report), condensed (tall news headline).",
      +      "enum": [
      +        "classic",
      +        "modern",
      +        "serif",
      +        "typewriter",
      +        "condensed"
      +      ],
      +      "title": "Title Font",
      +      "type": "string"
      +    },
      +    "title_size": {
      +      "default": "medium",
      +      "description": "medium (default); small for a long title, large for 3-6 words.",
      +      "enum": [
      +        "small",
      +        "medium",
      +        "large"
      +      ],
      +      "title": "Title Size",
      +      "type": "string"
      +    }
      +  },
      +  "title": "Frame",
      +  "type": "object"
      +}
    • addedInput schema / $defs / Plan / properties / frame
      Added value: +{
      +  "anyOf": [
      +    {
      +      "$ref": "#/$defs/Frame"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "Optional vertical frame (MONTAGE_FRAME) for a 16:9 montage posted as a Short / Reel / TikTok: picture at native size in a 9:16 frame, fixed title above with **accented** words, optional period look, speech pace. Best with subtitles {\"auto\": true, \"style\": \"word\"} (one word at a time)."
      +}
    • addedInput schema / $defs / Subtitles / properties / position
      Added value: +{
      +  "default": "auto",
      +  "description": "Where the subtitles sit on the picture: auto (default: low on a vertical video; bottom of the picture in a vertical frame), bottom, center or top of the picture. center and top cover the face of someone speaking to camera: only for shots without a face there.",
      +  "enum": [
      +    "auto",
      +    "bottom",
      +    "center",
      +    "top"
      +  ],
      +  "title": "Position",
      +  "type": "string"
      +}
    • changedInput schema / $defs / Subtitles / properties / style / description
      Previous value: -"shorts (default): one text at a time, bold capitals, keywords in a light colour, a dark brand-coloured box following the spoken word; the hooks show alone before the speech and their *accents* become keywords. classic: white outlined lines, hooks shown separately."New value: +"shorts (default): one text at a time, bold capitals, keywords in a light colour, a dark brand-coloured box following the spoken word; the hooks show alone before the speech and their *accents* become keywords. classic: white outlined lines, hooks shown separately. word (SUBTITLE_STYLES): ONE big lowercase word at a time, on the voice, keywords in yellow or blue (picked from the video). bold (SUBTITLE_STYLES): two or three big capital words at a time, keywords in yellow or blue, light shadow, no box."
    • changedInput schema / $defs / Subtitles / properties / style / enum
      Previous value: -[
      -  "shorts",
      -  "classic"
      -]New value: +[
      +  "shorts",
      +  "classic",
      +  "word",
      +  "bold"
      +]
    • addedInput schema / properties / body / type
      Added value: +"object"
  6. Changed3 schema fields changed
    • addedInput schema / $defs / Panel
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "« Cours » panel (MONTAGE_PANELS): the face slides to one side with a slow zoom, the other side darkens, a yellow\ntitle then short lines appear one by one on their words, like a lesson.",
      +  "properties": {
      +    "at_words": {
      +      "default": "",
      +      "description": "Spoken words on which the panel opens.",
      +      "maxLength": 80,
      +      "title": "At Words",
      +      "type": "string"
      +    },
      +    "end": {
      +      "anyOf": [
      +        {
      +          "exclusiveMinimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "title": "End"
      +    },
      +    "group": {
      +      "anyOf": [
      +        {
      +          "type": "integer"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Server-computed slide group; leave empty.",
      +      "title": "Group"
      +    },
      +    "lines": {
      +      "items": {
      +        "$ref": "#/$defs/PanelLine"
      +      },
      +      "maxItems": 6,
      +      "title": "Lines",
      +      "type": "array"
      +    },
      +    "scale": {
      +      "default": 1,
      +      "description": "Zoom while the face slides aside (1 = none, sharpest).",
      +      "maximum": 1.3,
      +      "minimum": 1,
      +      "title": "Scale",
      +      "type": "number"
      +    },
      +    "side": {
      +      "default": "auto",
      +      "description": "Side of the text (the face goes to the other side). auto = close panels share one slide, and the side alternates from one slide to the next.",
      +      "enum": [
      +        "auto",
      +        "left",
      +        "right"
      +      ],
      +      "title": "Side",
      +      "type": "string"
      +    },
      +    "start": {
      +      "anyOf": [
      +        {
      +          "minimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "title": "Start"
      +    },
      +    "title": {
      +      "default": "",
      +      "description": "Yellow title (max 48), e.g. \"Option 1 : la donation\".",
      +      "maxLength": 48,
      +      "title": "Title",
      +      "type": "string"
      +    },
      +    "until_words": {
      +      "default": "",
      +      "description": "Optional: spoken words after which it closes (else: next panel or long enough to read).",
      +      "maxLength": 80,
      +      "title": "Until Words",
      +      "type": "string"
      +    }
      +  },
      +  "title": "Panel",
      +  "type": "object"
      +}
    • addedInput schema / $defs / PanelLine
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "One short line of a « cours » panel, written on the spoken words it echoes.",
      +  "properties": {
      +    "at_words": {
      +      "default": "",
      +      "description": "Spoken words on which the line appears (copied as said, no figures). Empty = spread over the panel.",
      +      "maxLength": 80,
      +      "title": "At Words",
      +      "type": "string"
      +    },
      +    "start": {
      +      "anyOf": [
      +        {
      +          "minimum": 0,
      +          "type": "number"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ],
      +      "description": "Server-computed; leave empty.",
      +      "title": "Start"
      +    },
      +    "text": {
      +      "description": "Short line (max 80), *word* = yellow accent.",
      +      "maxLength": 80,
      +      "minLength": 1,
      +      "title": "Text",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "text"
      +  ],
      +  "title": "PanelLine",
      +  "type": "object"
      +}
    • addedInput schema / $defs / Plan / properties / panels
      Added value: +{
      +  "description": "Optional « cours » panels (MONTAGE_PANELS): face to one side, darkened side with a yellow title and lines written on the words.",
      +  "items": {
      +    "$ref": "#/$defs/Panel"
      +  },
      +  "maxItems": 8,
      +  "title": "Panels",
      +  "type": "array"
      +}
  7. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) it discloses the replacement semantics that matter most: "Send the complete plan: omitted finishing touches are removed" and "Preserve prior clips except requested changes", i.e. the plan is a full overwrite of the finishing layer but not of the clips. It also states the precondition that only already-selected job_ids are accepted, which the annotations cannot express.

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 critical constraints are front-loaded and every sentence carries real information about units or replacement behaviour. The trailing "Arguments: {...}" block largely repeats what the input schema already declares, which is the one piece of redundancy in an otherwise dense definition.

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 a huge nested schema, the description supplies the things the schema cannot: the two time bases, the overwrite rule for finishing touches, and the approval gate before rendering. Missing are the return/confirmation behaviour (no output schema exists) and how a stale or mismatched version in the body is handled.

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?

The schema documents nested fields richly but leaves the top-level units ambiguous, and the description fills exactly that gap: clip start/end are "source seconds", speed is "x0.25–x4", while all finishing touches use "FINAL montage seconds". It also pins the payload shape with a concrete example including version 3. It does not explain what path.id identifies (plan/project id) or what a version mismatch does.

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 opening sentence gives a specific verb and resource ("Save an external assistant's structured edit plan") and immediately scopes it by naming what it does NOT do ("without invoking a planner or rendering"), which separates it from kelpo_start_editing, kelpo_preview_editing and kelpo_finalize_editing. An agent can identify the operation 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It places the call in a workflow: "Show the full recap and request explicit approval before render_editing", and constrains input with "Only selected job_ids are allowed". It stops short of naming a sibling to use instead when the agent wants to preview or render, so the routing is clear but not exhaustive.

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