Skip to main content
Glama

Draw a music video's cast

draw_music_video_cast

Draws the people the user kept as character sheets (spends credits) Only after the user's yes to the people and the price. people: the ones kept, by index (the others are declined), each with an edited name or description if the user changed it, or character: a kit character's handle (list_characters) in that role instead, free. An empty list keeps it to the artist (nobody else is cast). credits must be price.per_person times the people drawn (0 when none is); another price answers 409 with the current one. Each description is read first like start_character's describe mode (one made-up adult, never a real or famous person: 422 naming the person's index). One hold for all; each sheet is drawn plain (base clothes, the person only: the video dresses them later), charged once it passes its check, and kept in the song artist's kit as AI-made, not shared. Poll get_music_video_casting until ready, then add people_for_brief to people. Needs an active plan (402 plan_required without one; get_account: plan.active).

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": {
      "casting_id": "<casting_id>",
      "credits": "<credits>",
      "people": "<people>"
    },
    "name": "draw_music_video_cast"
  }
}

Input Schema

NameRequiredDescriptionDefault
peopleYesThe people kept: [{"index":1},{"index":2,"description":"…"},{"index":3,"character":"mia-torres"}]; [] keeps it to the artist
creditsYesThe price shown: price.per_person × the people drawn
casting_idYesThe casting id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Goes far past the annotations: spends credits, exact price formula, 409 on a stale price with the current one returned, 422 on a real/famous-person description with the offending index, one hold for all sheets, charging only after the check passes, and the resulting asset landing in the artist's kit as AI-made and unshared. The 402 plan_required gate is also disclosed.

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 action and the credit cost, and nearly every clause carries information. It is written as dense run-on fragments with nested parentheticals, which slows parsing of an otherwise information-rich description.

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, so the description compensates by naming the polling tool, the state transition (people_for_brief on people), the per-sheet hold/charge timing, and the 402/409/422 failure modes. Nothing an agent needs in order to call it correctly appears to be 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% and the schema already documents the credits formula and the empty-list case, but the description still adds real meaning: index identifies kept people while others are declined, name/description overrides come from user edits, and character points at a list_characters handle. The conflict semantics for credits (409) are the main addition the schema cannot express.

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 ('Draws the people the user kept as character sheets') and scopes it to the kept/declined split, which separates it from cast_music_video and draw_character_sheet 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 precondition ('Only after the user's yes to the people and the price'), an explicit alternative path ('character: a kit character's handle (list_characters) … free'), an edge case ('An empty list keeps it to the artist'), and a follow-up ('Poll get_music_video_casting until ready'). This is close to a complete decision rule.

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