Skip to main content
Glama

Launch film from a website

make_launch_film
Destructive

Turns a product website or app listing into a 20–40 second launch film, rendering an MP4 with music and sound effects from the page’s own brand and content.

Instructions

Use it when the user wants a launch video, product video, promo, teaser or announcement clip for a product's site or app. Makes a 20 to 40 second launch film from a product's own site in one job: it reads the brand and the page, plans the film (name and promise, the real screen in a browser window, the page's own headline, feature cards, a number the page states when it finds one, the logo close) and renders film.mp4 with music and sound effects, with Chrome and ffmpeg on this machine. Nothing is generated by AI: the film shows what the site says. The result shows film.json, the plan, next to words.json, the page's words, and frames/sheet.jpg has two stills a clip. The film is 25 frames a second at 1920x1080 or 1080x1920, its sound about -14 LUFS. Its music is the look's own, or a track of the user's that film.json names. For the user's own track, plan with music false and give the rendered film to fit_music as video. For a plan to read or change before it renders, use plan_launch_film instead. The address needs a dot in its host name, so localhost on its own is refused. The launch-film playbook (makersmcp_playbook) has the whole job. (launch-film 0.3.1, on this machine.)

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": {
      "url": "<url>"
    },
    "name": "make_launch_film"
  }
}

Input Schema

NameRequiredDescriptionDefault
sfxNoSet to false to leave out the sound effects.
urlYesThe product's website, like https://linear.app, or its App Store or Google Play listing. A social profile is refused, and so is a host without a dot, like localhost.
jobsNoClips rendered at once (default 2). 1 suits a slow machine.
keepNoKeep the work files, each clip's MP4, in a launch-film-work- folder in the system's temp folder, outside the film's folder; the summary names it.
lookNoThe film's look, which also sets the tempo of its music and so how long a bar lasts (default: picked from the brand). launch_film_guide with topic looks says what each one suits.
brandNoA brand kit you already have: its folder or its brand.json. make_brand_kit makes one. The kit copies the kit given into brand/ in the film's folder; without one, it reads the brand from the site itself.
musicNoSet to false to leave out the look's music bed, as when the user's own track goes under the film later.
wordsNoA words.json from an earlier plan or film, used instead of reading the page again, so a second aspect keeps the same words.
aspectNo16:9 (default) or 9:16 for phones. For both, make the second one with words from the first.
out_dirNoFolder to save into, absolute or relative to /app. Default: launch-film-<host>, where <host> is the site's host without www or the port. A run replaces the files an earlier run of this kit left there, so give each version its own out_dir. The kit deletes the brand/ folder in it and makes it again when given brand, or for an App Store page, so it does not start then while that folder holds a file other than a kit's own that would be lost. Otherwise it makes the kit in brand/ again where it is, so it does not start while brand/ holds a file named like a kit's own, in any letter case, that its brand.json does not list. To use that brand/ folder where it is, give brand as out_dir with /brand added, written the same way.
secondsNoAim for this length (default 30). Clips last whole bars of the look's music and the plan never stretches one to fill the time, so the film can end several seconds away from it, often short; film.timeline.json has its exact length.
wait_secondsNoHow long to wait for the result, counted from the start of the call, before returning a job_id to wait on. Some clients end a call after 60 or 240 seconds; 45 is safe in all of them.

Output Schema

NameRequiredDescriptionDefault
kitYes
docsNoThe notes the text shows, and where each one is.
nextNoWhat to do next, as the Next line says.
toolYes
filesNo
folderNoWhere the kit saved its files.
job_idYes
passedNoFor checks: whether the check passed.
statusYes
continuedNoTrue when this call continued the job of an identical call whose answer did not reach the client, instead of starting another.
exit_codeNo
last_lineNoWhat the kit was doing last.
expires_atNoWhen the download links stop working.
next_actionNo
elapsed_secondsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changedv0.2.0
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / aspect / description
      Previous value: -"16:9 (default) or 9:16 for phones."New value: +"16:9 (default) or 9:16 for phones. For both, make the second one with words from the first."
    • changedInput schema / properties / brand / description
      Previous value: -"A brand kit you already have: an easybrandkit folder or its brand.json."New value: +"A brand kit you already have: its folder or its brand.json. make_brand_kit makes one. The kit copies the kit given into brand/ in the film's folder; without one, it reads the brand from the site itself."
    • changedInput schema / properties / jobs / description
      Previous value: -"Clips rendered at once (default 2)."New value: +"Clips rendered at once (default 2). 1 suits a slow machine."
    • changedInput schema / properties / keep / description
      Previous value: -"Keep the work files, each clip's MP4."New value: +"Keep the work files, each clip's MP4, in a launch-film-work- folder in the system's temp folder, outside the film's folder; the summary names it."
    • changedInput schema / properties / look / description
      Previous value: -"The film's look (default: picked from the brand). launch_film_guide with topic looks says what each one suits."New value: +"The film's look, which also sets the tempo of its music and so how long a bar lasts (default: picked from the brand). launch_film_guide with topic looks says what each one suits."
    • changedInput schema / properties / music / description
      Previous value: -"Set to false to leave out the music bed."New value: +"Set to false to leave out the look's music bed, as when the user's own track goes under the film later."
    • changedInput schema / properties / out_dir / description
      Previous value: -"Folder to save into, absolute or relative to /app. Default: launch-film-{host}. The kit deletes the brand/ folder in it and makes it again when given brand, or for an App Store page, so it does not start then while that folder holds a file other than a kit's own that would be lost. Otherwise it makes the kit in brand/ again where it is, so it does not start while brand/ holds a file named like a kit's own, in any letter case, that its brand.json does not list. To use that brand/ folder where it is, give brand as out_dir with /brand added, written the same way."New value: +"Folder to save into, absolute or relative to /app. Default: launch-film-<host>, where <host> is the site's host without www or the port. A run replaces the files an earlier run of this kit left there, so give each version its own out_dir. The kit deletes the brand/ folder in it and makes it again when given brand, or for an App Store page, so it does not start then while that folder holds a file other than a kit's own that would be lost. Otherwise it makes the kit in brand/ again where it is, so it does not start while brand/ holds a file named like a kit's own, in any letter case, that its brand.json does not list. To use that brand/ folder where it is, give brand as out_dir with /brand added, written the same way."
    • changedInput schema / properties / seconds / description
      Previous value: -"Aim for this length (default 30)."New value: +"Aim for this length (default 30). Clips last whole bars of the look's music and the plan never stretches one to fill the time, so the film can end several seconds away from it, often short; film.timeline.json has its exact length."
    • changedInput schema / properties / url / description
      Previous value: -"The product's website, like https://linear.app"New value: +"The product's website, like https://linear.app, or its App Store or Google Play listing. A social profile is refused, and so is a host without a dot, like localhost."
    • changedInput schema / properties / wait_seconds / description
      Previous value: -"How long to wait for the result before returning a job_id to wait on. 45 is safe for clients that stop a tool call after 60 seconds."New value: +"How long to wait for the result, counted from the start of the call, before returning a job_id to wait on. Some clients end a call after 60 or 240 seconds; 45 is safe in all of them."
    • changedInput schema / properties / words / description
      Previous value: -"A words.json you already have, instead of reading the page again."New value: +"A words.json from an earlier plan or film, used instead of reading the page again, so a second aspect keeps the same words."
    • addedOutput schema / properties / continued
      Added value: +{
      +  "description": "True when this call continued the job of an identical call whose answer did not reach the client, instead of starting another.",
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / docs
      Added value: +{
      +  "description": "The notes the text shows, and where each one is.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "name": {
      +        "type": "string"
      +      },
      +      "path": {
      +        "type": "string"
      +      },
      +      "url": {
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "name"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / next
      Added value: +{
      +  "description": "What to do next, as the Next line says.",
      +  "type": "string"
      +}
  2. Changed3 schema fields changed
    • changedInput schema / properties / out_dir / description
      Previous value: -"Folder to save into, absolute or relative to /app. Default: launch-film-{host}."New value: +"Folder to save into, absolute or relative to /app. Default: launch-film-{host}. The kit deletes the brand/ folder in it and makes it again when given brand, or for an App Store page, so it does not start then while that folder holds a file other than a kit's own that would be lost. Otherwise it makes the kit in brand/ again where it is, so it does not start while brand/ holds a file named like a kit's own, in any letter case, that its brand.json does not list. To use that brand/ folder where it is, give brand as out_dir with /brand added, written the same way."
    • addedOutput schema / properties / expires_at
      Added value: +{
      +  "description": "When the download links stop working.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / files / items / properties / url
      Added value: +{
      +  "description": "Where to download the file, when the job ran on a server.",
      +  "type": "string"
      +}
  3. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description corroborates this by warning that a run replaces files an earlier run left in out_dir and deletes/recreates brand/. It adds real context beyond annotations: local Chrome/ffmpeg rendering, no AI generation, output specs (25fps, 1920x1080/1080x1920, -14 LUFS). It stops short of stating runtime or failure modes, so not a 5.

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 the trigger and the core job, then outputs, then alternatives. It is dense and a few clauses are run-on (the music/track sentence), but nearly every sentence carries actionable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, destructive, open-world render tool with an output schema, the description covers trigger, alternatives, output artifacts, rendering environment, and the destructive out_dir behavior. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning: music=false for a user's own track, words reuse to keep a second aspect consistent, and seconds often ending short of the target. These clarify intent beyond the schema's field-level text.

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 ('Makes a 20 to 40 second launch film from a product's own site in one job') and enumerates the concrete artifacts (film.mp4, film.json, words.json, frames/sheet.jpg). It explicitly distinguishes itself from plan_launch_film, so an agent can route without opening either 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?

Opens with an explicit trigger ('Use it when the user wants a launch video, product video, promo, teaser or announcement clip') and names the alternative for the read/change case ('use plan_launch_film instead'). It also routes the user-track case to fit_music, covering when-not and alternatives.

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