Skip to main content
Glama

plan_character_film

Read-only

Plan a Character Film: pick a narrator, type a topic, and get a full-length block script saved as a project. Film scripts are directed by Anthropic’s Claude Opus 5.5. Does not render or charge. Next: generate_character_film for the opening, then continue_character_film for the rest.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topicYesWhat the narrator should explain. One topic, one film.
lookIdNoIgnored. The narrator’s fixed look is used. Kept so older agents that still send lookId do not hard-fail.
voiceIdNoIgnored. The narrator’s fixed voice is used. Kept so older agents that still send voiceId do not hard-fail.
narratorIdYesNarrator id from list_character_film_catalog. The narrator is the whole character: its look and voice are used; there is no separate look or voice choice.
aspectRatioNoFrame size. 16:9 landscape (default) or 9:16 vertical.16:9
lengthSecondsYesFull film length in seconds (30, 60, 120, or 180). The opening (block 1, at most 8 seconds) renders first; continue_character_film films the rest.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleNoPlanned film title.
topicNoTopic this film explains.
blocksNoOrdered script blocks. Block 1 is the opening (at most 8 seconds).
lookIdNoLook id locked on this project.
videoIdNoLibrary clip id for this job, when one exists.
voiceIdNoVoice id locked on this project.
createdAtNoISO timestamp when this project was created.
projectIdYesProject id. Pass this to quote_character_film, generate_character_film, continue_character_film, and get_character_film.
narratorIdNoNarrator id locked on this project.
aspectRatioNoFrame size, 16:9 or 9:16.
totalSecondsNoSum of block durations in seconds.
lengthSecondsNoFull planned film length in seconds.
openingSecondsNoDuration of block 1, at most 8 seconds.
narratorSheetUrlNoNarrator model-sheet still once the first render has drawn it, or null.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / lookId / description
      Previous value: -"Illustration look id from list_character_film_catalog (the style of every frame)."New value: +"Ignored. The narrator’s fixed look is used. Kept so older agents that still send lookId do not hard-fail."
    • removedInput schema / properties / lookId / enum
      Removed value: -[
      -  "claymation",
      -  "watercolor-anime",
      -  "ligne-claire",
      -  "crayon",
      -  "marker-sketch",
      -  "gouache-storybook",
      -  "paper-cutout",
      -  "pixel"
      -]
    • changedInput schema / properties / narratorId / description
      Previous value: -"Narrator id from list_character_film_catalog. The narrator’s voice is used; there is no separate voice choice."New value: +"Narrator id from list_character_film_catalog. The narrator is the whole character: its look and voice are used; there is no separate look or voice choice."
    • changedInput schema / properties / narratorId / enum
      Previous value: -[
      -  "nib",
      -  "kiko",
      -  "stella",
      -  "rex",
      -  "rio",
      -  "wren",
      -  "juno",
      -  "mina"
      -]New value: +[
      +  "pip",
      +  "mo",
      +  "lulu",
      +  "hazel",
      +  "otto",
      +  "rose",
      +  "bo",
      +  "sage",
      +  "wren",
      +  "kiko",
      +  "tally",
      +  "nib",
      +  "chalk",
      +  "rio",
      +  "juno",
      +  "yumi",
      +  "kenji",
      +  "dot",
      +  "patch",
      +  "ada",
      +  "marlo",
      +  "ollie",
      +  "zara",
      +  "barnaby",
      +  "momo",
      +  "bea",
      +  "rex",
      +  "nova",
      +  "gus",
      +  "tock",
      +  "fern",
      +  "duke",
      +  "lumi",
      +  "taro",
      +  "oya",
      +  "bolt",
      +  "reginald",
      +  "pepper",
      +  "lola",
      +  "moss",
      +  "noor",
      +  "arlo",
      +  "mei",
      +  "chip",
      +  "bruno",
      +  "stella",
      +  "kai",
      +  "plume",
      +  "grumble",
      +  "quill"
      +]
    • changedInput schema / required
      Previous value: -[
      -  "topic",
      -  "narratorId",
      -  "lookId",
      -  "lengthSeconds"
      -]New value: +[
      +  "topic",
      +  "narratorId",
      +  "lengthSeconds"
      +]
  2. Changed3 schema fields changed
    • changedInput schema / properties / narratorId / description
      Previous value: -"Narrator id from list_character_film_catalog (who tells the story)."New value: +"Narrator id from list_character_film_catalog. The narrator’s voice is used; there is no separate voice choice."
    • changedInput schema / properties / voiceId / description
      Previous value: -"Narration voice id from list_audio_lab_voices. Same catalog as Audio Lab / Story."New value: +"Ignored. The narrator’s fixed voice is used. Kept so older agents that still send voiceId do not hard-fail."
    • changedInput schema / required
      Previous value: -[
      -  "topic",
      -  "narratorId",
      -  "lookId",
      -  "voiceId",
      -  "lengthSeconds"
      -]New value: +[
      +  "topic",
      +  "narratorId",
      +  "lookId",
      +  "lengthSeconds"
      +]
  3. Changed2 schema fields changed
    • removedInput schema / properties / captionStyle
      Removed value: -{
      -  "default": "spotlight",
      -  "description": "Burned-in caption look from the Story catalog: off, spotlight (default), impact, highlighter, editorial, boxed, or kicker. Shared with Story and Topic Shorts. Does not change the quote. Caption failure still ships the film.",
      -  "enum": [
      -    "off",
      -    "spotlight",
      -    "impact",
      -    "highlighter",
      -    "editorial",
      -    "boxed",
      -    "kicker"
      -  ],
      -  "type": "string"
      -}
    • removedOutput schema / properties / captionStyle
      Removed value: -{
      -  "description": "Burned-in caption look from the Story catalog.",
      -  "type": "string"
      -}
  4. Changed3 schema fields changed
    • changedInput schema / properties / lengthSeconds / description
      Previous value: -"Full film length in seconds (30, 60, 120, or 180). The opening (block 1, at most 15 seconds) renders first; continue_character_film films the rest."New value: +"Full film length in seconds (30, 60, 120, or 180). The opening (block 1, at most 8 seconds) renders first; continue_character_film films the rest."
    • changedOutput schema / properties / blocks / description
      Previous value: -"Ordered script blocks. Block 1 is the opening (at most 15 seconds)."New value: +"Ordered script blocks. Block 1 is the opening (at most 8 seconds)."
    • changedOutput schema / properties / openingSeconds / description
      Previous value: -"Duration of block 1, at most 15 seconds."New value: +"Duration of block 1, at most 8 seconds."
  5. Added

TDQS

A3.5/5.0
Behavior1/5

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

The description states the call results in a script 'saved as a project', i.e. a persisted server-side artifact, while the annotations declare readOnlyHint=true. This is the same class of inconsistency as a 'creates/records' description paired with a read-only hint; the extra disclosures about no rendering/charging and the directing model are useful but do not resolve the conflict.

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?

Three tight sentences: purpose first, behavioral constraints (no render/charge) second, routing third. Nothing is padded, though the Claude Opus 5.5 attribution is flavor more than actionable guidance.

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?

With an output schema present, return values need not be explained, and the description covers what is produced, its persistence, that nothing renders or bills, and the follow-up tool sequence. The main omissions are the dependency on list_character_film_catalog for narratorId and any statement about whether the plan is reused or replaced on repeat calls.

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

Parameters3/5

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

Schema description coverage is 100%, including semantics for the deliberately ignored lookId/voiceId and the narrator-as-whole-character rule, so the schema already carries parameter meaning. The description only restates the inputs at a high level ('pick a narrator, type a topic') and adds nothing about length or aspect choices, which is the expected baseline when the schema does the heavy lifting.

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 concrete verb+resource (plan a Character Film) plus the concrete output (a full-length block script saved as a project) and the inputs involved (narrator, topic). It also explicitly separates itself from the render siblings by noting it 'Does not render or charge' and naming generate_character_film and continue_character_film as the later stages.

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?

Gives explicit sequencing: this tool first, then generate_character_film for the opening, then continue_character_film for the remainder, and 'Does not render or charge' signals when this cheap step is appropriate. It stops short of stating prerequisites (e.g. that the narrator id must come from list_character_film_catalog) or an explicit 'do not call this if you already have a script' exclusion.

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