Skip to main content
Glama

Set actor

set_actor
Destructive

Casts the on-camera narrator and renders their portrait, which every scene is generated from — the app's actor form. Leave archetype out to cast someone fitting the audience automatically. Pass archetype to design them: for a project with an actor, only the fields you give change (e.g. just clothing); a first actor needs every field except facialFeatures. Also sets the narrator's spoken language and accent (language, language_accent) when given; to change only those, use set_narrator_voice, which doesn't recast. Each call renders a new portrait (7 credits, 10 on Premium). Show the user previewUrl: it is the actor Retiplex uses; never generate or substitute a picture of them yourself.

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": {
      "project_id": "<project_id>"
    },
    "name": "set_actor"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageNoAsk the user which language the ad is spoken in unless it is obvious (a Spanish market means "es"). Default en. One of: en (English), cs (Czech), nl (Dutch), de (German), it (Italian), pl (Polish), sk (Slovak), es (Spanish). Set it BEFORE the creative brief and script (create_project or set_narrator_voice): they are written in it.
archetypeNo
project_idYesThe project's id.
language_accentNoOptional regional accent, e.g. "Castilian Spanish" or "Mexican Spanish". Defaults to a native accent of the language; changing the language clears it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only say readOnly=false, destructive=true, openWorld=false; the description goes much further by disclosing the credit cost (7, 10 on Premium), that every call re-renders and replaces the portrait, the partial-vs-full update semantics, and the mandate to show the user previewUrl rather than substituting an image.

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 core action and cost-free of filler, but three long em-dash-clause sentences pack several independent rules together, so the update-semantics and voice-routing details take a careful read rather than being scan-friendly.

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 4-parameter mutation with no output schema, the description covers everything an agent needs: cost, recast behavior, partial-update rules, required first-actor fields, language ordering, the previewUrl return value, and the alternative tool for voice-only changes.

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

Parameters5/5

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

Schema coverage is 75% and the nested archetype object is only partly documented, but the description supplies the missing meaning: archetype omitted = audience-fit auto-cast, archetype supplied = partial patch on existing actors / full design on the first actor, plus the language/accent interaction where changing language clears the accent.

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 ("Casts the on-camera narrator and renders their portrait") and adds the key scope fact that every scene derives from that portrait. It also names the sibling set_narrator_voice and what that one does differently, so an agent can separate them without reading schemas.

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?

Gives explicit branching: omit `archetype` for automatic casting, pass it to design the actor; for an existing actor only supplied fields change, whereas a first actor needs every field except facialFeatures. It also routes the language/accent-only case to set_narrator_voice with the reason (no recast).

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