Skip to main content
Glama
delano
by delano

create_api_schema

Create an API schema by providing the API ID, schema type, and schema files. Supports various schema formats like Proto, GraphQL, OpenAPI, RAML, WSDL, and AsyncAPI.

Instructions

Create a schema for an API

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
apiIdYesAPI ID
typeYesSchema type
filesYesSchema files

Implementation Reference

  • The createApiSchema handler method in the ApiTools class. Validates that apiId, type, and files are provided, then makes a POST request to /apis/{apiId}/schemas.
    /**
     * Create a schema for an API
     * @param args Parameters including apiId (required), type (required), files (required)
     */
    async createApiSchema(args: any): Promise<ToolCallResponse> {
      if (!args.apiId || !args.type || !args.files) {
        throw new McpError(ErrorCode.InvalidParams, 'apiId, type, and files are required');
      }
      const { apiId, ...data } = args;
      const response = await this.client.post(`/apis/${apiId}/schemas`, data);
      return this.createResponse(response.data);
    }
  • The CreateApiSchemaRequest interface defining the request schema: type (ApiSchemaType enum) and files (array of SchemaFile objects).
    export interface CreateApiSchemaRequest {
      type: ApiSchemaType;
      files: SchemaFile[];
    }
  • The tool definition for 'create_api_schema' registered in TOOL_DEFINITIONS, specifying inputSchema with apiId, type (enum from ApiSchemaType), and files (array of path/content/root objects).
    {
      name: 'create_api_schema',
      description: 'Create a schema for an API',
      inputSchema: {
        type: 'object',
        properties: {
          apiId: {
            type: 'string',
            description: 'API ID',
          },
          type: {
            type: 'string',
            enum: Object.values(ApiSchemaType),
            description: 'Schema type',
          },
          files: {
            type: 'array',
            description: 'Schema files',
            items: {
              type: 'object',
              properties: {
                path: {
                  type: 'string',
                  description: 'File path',
                },
                content: {
                  type: 'string',
                  description: 'File content',
                },
                root: {
                  type: 'object',
                  properties: {
                    enabled: {
                      type: 'boolean',
                      description: 'Tag as root file (protobuf only)',
                    },
                  },
                },
              },
              required: ['path', 'content'],
            },
          },
        },
        required: ['apiId', 'type', 'files'],
      },
    },
  • The switch-case registration in handleToolCall that routes 'create_api_schema' to the createApiSchema method.
    case 'create_api_schema':
      return await this.createApiSchema(args);
  • The ApiSchemaType enum listing all supported schema types (PROTO2, PROTO3, GRAPHQL, OPENAPI_3_1, etc.) used as validation for the 'type' field.
    export enum ApiSchemaType {
      PROTO2 = 'proto:2',
      PROTO3 = 'proto:3',
      GRAPHQL = 'graphql',
      OPENAPI_3_1 = 'openapi:3_1',
Behavior2/5

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

No annotations are provided, so the description must disclose behavioral traits. It only states 'create a schema', giving no information about side effects, permissions, or limitations. The create action implies mutation but no further detail.

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?

The description is a single short sentence, very concise. However, it may be too minimal, but it is efficient with no wasted words.

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

Completeness2/5

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

Given the three required parameters and no output schema, the description is insufficient. It doesn't explain the enum for type, the nested structure of files, or what the tool returns. The agent might struggle to invoke it correctly without additional context.

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?

The input schema covers all parameters with descriptions (100% coverage). The description adds no extra meaning beyond what the schema already provides. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'create a schema for an API', which is a specific verb and resource. However, it doesn't differentiate from sibling tools like 'create_api' or 'sync_collection_with_schema', which could be ambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like 'update_schema_file'. No prerequisites mentioned (e.g., the API must already exist). The agent has no context for decision-making.

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/delano/postman-mcp-server'

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