Skip to main content
Glama

openart_create_character

Create an OpenArt character from an image by providing a name and local file path, with optional background story and voice ID.

Instructions

Create a new OpenArt character from an image. Provide name, local image path, optional background story, optional voice ID.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
image_pathYesAbsolute local file path to the character image
background_storyNo
voice_idNo

Implementation Reference

  • The handler function `createCharacter` that implements the character creation logic via Playwright browser automation on OpenArt's website.
    export async function createCharacter(params: {
      name: string;
      image_path: string;
      background_story?: string;
      voice_id?: string;
    }): Promise<Character> {
      const page = await newPage();
      try {
        await page.goto(`${BASE_URL}/suite/characters-and-worlds`);
        await page.waitForLoadState("networkidle");
    
        // TODO: real selectors. Approximate flow:
        await page.locator('button:has-text("Create Character")').click();
        await page.locator('input[name="name"]').fill(params.name);
        await page.locator('input[type="file"]').setInputFiles(params.image_path);
        if (params.background_story) {
          await page.locator('textarea[name="background_story"]').fill(params.background_story);
        }
        if (params.voice_id) {
          await page.locator(`[data-voice-id="${params.voice_id}"]`).click();
        }
        await page.locator('button:has-text("Create")').click();
        await page.waitForURL(/\/character\/.+/);
    
        const id = page.url().split("/character/").pop() || "";
        return {
          id,
          name: params.name,
          url: page.url(),
        };
      } finally {
        await page.close();
      }
    }
  • The input schema / type definition for the openart_create_character tool.
    {
      name: "openart_create_character",
      description:
        "Create a new OpenArt character from an image. Provide name, local image path, optional background story, optional voice ID.",
      inputSchema: {
        type: "object",
        properties: {
          name: { type: "string" },
          image_path: { type: "string", description: "Absolute local file path to the character image" },
          background_story: { type: "string" },
          voice_id: { type: "string" },
        },
        required: ["name", "image_path"],
      },
  • src/index.ts:96-104 (registration)
    The registration / dispatch logic that routes the 'openart_create_character' tool call to the createCharacter handler with Zod validation.
    case "openart_create_character":
      result = await createCharacter(
        z.object({
          name: z.string(),
          image_path: z.string(),
          background_story: z.string().optional(),
          voice_id: z.string().optional(),
        }).parse(args)
      );
  • The `newPage` helper used by createCharacter to get a Playwright page with a logged-in browser context.
    export async function newPage(): Promise<Page> {
      const ctx = await getContext();
      return ctx.newPage();
    }
Behavior3/5

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

Annotations already declare destructiveHint=false and openWorldHint=true. The description adds little behavioral context beyond the creation action; it does not mention auth requirements, rate limits, or consequences of invalid inputs. With annotations carrying some of the burden, the description is adequate but not enriching.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the action and lists the parameters. No unnecessary words or redundancy.

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

Completeness3/5

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

The description covers the core purpose and parameter roles, but omits important context: no indication of the return value (e.g., character ID), no mention that the image file must exist locally, and no explanation of the openWorldHint annotation's implications. Given no output schema, return format info would be valuable.

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 only 25% (only image_path described). The description lists the parameters and explicitly marks background_story and voice_id as optional, but does not add format constraints or examples for the undocumented parameters (name, background_story, voice_id). It adds marginal value over the parameter names.

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?

The description explicitly states the action 'Create a new OpenArt character from an image' and lists the required parameters (name, image_path) and optional parameters. It clearly distinguishes from siblings like openart_get_character (retrieve) and openart_list_characters (list).

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?

The description clearly indicates when to use the tool (to create a character from an image), but it does not provide explicit guidance on when not to use it or compare it directly to sibling tools, though the verb 'create' implies the primary use case.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jbertus/openart-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server