Skip to main content
Glama

Create a character episode

create_character_episode
Idempotent

Make the episode: 3-8 shots, 12-60 seconds, the same fictional character in every shot, narrated with captions. CHARGES credits (up to 313 credits for a default 12-second episode; longer ones (up to 60 seconds) cost more). ALWAYS call quote_character_episode first and tell the human the price: the human, not the agent, decides to spend. This tool refuses unless confirm is true, expectedCredits equals the price computed now (a changed price answers 409 PRICE_CHANGED and charges nothing) and idempotencyKey is set; StoryShort has no daily spending cap per key, so these are the guard. The series must have a REVIEWED, CONFIRMED season plan and the episode must be one of its episodes exactly as planned (SEASON_PLAN_REQUIRED / SEASON_NOT_REVIEWED / EPISODE_NOT_IN_PLAN otherwise, with a nextAction, nothing charged); the narrator voice, language, style, look and outfit come from the plan. Credits are held when it starts. A shot that cannot be animated keeps a still image and its clip credits go back; if too few shots move, or anything else fails, everything goes back. Characters are fictional adults (or animals / mascots), AI-generated: no real or famous people, no children or anyone who looks under 18, no sexual content, no logos or protected characters (refused with CONTENT_POLICY, nothing charged). Everything made here is AI-generated and labelled as such. Takes about 10-25 minutes: poll get_video with arguments { id: <the returned id / videoId> }; it reports status, stage and, when COMPLETED, videoUrl. One episode at a time per account. Requires the "video:create" scope.

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": {
      "seriesId": "<seriesId>",
      "confirm": "<confirm>",
      "expectedCredits": "<expectedCredits>",
      "idempotencyKey": "<idempotencyKey>"
    },
    "name": "create_character_episode"
  }
}

Input Schema

NameRequiredDescriptionDefault
shotsNoThe shots of the planned episode. Give `shots` OR `script`.
titleNoOptional title.
scriptNoThe narration, about 29-147 words. The system splits it into shots by sentence. Give `script` OR `shots`, exactly as planned (get_season_plan).
confirmYesMust be true: making an episode spends credits, and the human has seen the price.
sheetIdNoOmit it: the character sheet is the one the season plan names for this episode. If given it must equal that sheet.
languageNoOmit it: the narration language is the season plan's. If given it must equal the plan's.
seriesIdYesA series id from list_series whose season plan is reviewed and confirmed.
shotCountNoWith `script`: how many shots to split it into. Omit for an automatic count.
idempotencyKeyYesRequired. One new unique key per purchase; a repeat with the same key returns the first answer (replayed: true) and charges nothing.
expectedCreditsYesThe credits the quote showed the human. Must match the price computed now.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / script / description
      Previous value: -"The narration, about 74-147 words. The system splits it into shots by sentence. Give `script` OR `shots`, exactly as planned (get_season_plan)."New value: +"The narration, about 29-147 words. The system splits it into shots by sentence. Give `script` OR `shots`, exactly as planned (get_season_plan)."
    • changedInput schema / properties / script / minLength
      Previous value: -120New value: +60
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare non-readonly, non-destructive, idempotent and open-world; the description goes far beyond by explaining the credit ceiling (up to 313 for 12s), the 409 PRICE_CHANGED path that charges nothing, that credits are held at start and refunded per failed shot or fully on failure, the content policy refusal with nothing charged, the 10-25 minute runtime, and the required 'video:create' scope. That is exactly the operational context an agent needs before spending money.

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 what the tool makes and that it charges, then prerequisites, then failure/refund behaviour, then polling and scope. Dense and heavily parenthetical, with some re-statement of schema constraints (plan must be REVIEWED/CONFIRMED), but nearly every clause carries decision-relevant 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?

No output schema exists, and the description compensates by saying the call returns an id and that completion must be tracked via get_video { id: <returned id / videoId> }, which reports status, stage and videoUrl. Cost, error codes, timing and moderation limits are all covered, so nothing material is missing for a 10-parameter paid mutation.

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 baseline is 3; the description adds rationale the schema does not, notably why expectedCredits and idempotencyKey matter ('StoryShort has no daily spending cap per key, so these are the guard') and that shots/script/voice/language come from the reviewed season plan. It does not add format detail for shots fields such as action or camera, which the schema already covers.

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 and resource with full scope: 'Make the episode: 3-8 shots, 12-60 seconds, the same fictional character in every shot, narrated with captions.' That scope (character-consistent multi-shot episode) distinguishes it from create_video and draft_video without needing 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?

Explicit mandatory prerequisite ('ALWAYS call quote_character_episode first and tell the human the price: the human, not the agent, decides to spend'), explicit refusal conditions (confirm must be true, expectedCredits must match, idempotencyKey set), and an explicit concurrency limit ('One episode at a time per account'). It also names the sibling to poll afterwards (get_video) and the sibling that supplies the plan (get_season_plan).

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