Skip to main content
Glama

start_codegen_session

Start recording browser automation actions to generate Playwright test code with configurable output options for automated testing workflows.

Instructions

Start a new code generation session to record Playwright actions

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
optionsYesCode generation options

Implementation Reference

  • Primary implementation of the 'start_codegen_session' tool, including handler function that initializes a codegen session with ActionRecorder, merges options, ensures output directory, and returns session details.
    export const startCodegenSession: Tool = {
      name: "start_codegen_session",
      description: "Start a new code generation session to record MCP tool actions",
      parameters: {
        type: "object",
        properties: {
          options: {
            type: "object",
            description: "Code generation options",
            properties: {
              outputPath: { type: "string" },
              testNamePrefix: { type: "string" },
              includeComments: { type: "boolean" },
            },
          },
        },
      },
      handler: async ({ options = {} }: { options?: CodegenOptions }, _context?: { server?: any }) => {
        try {
          // Merge provided options with defaults
          const mergedOptions = { ...DEFAULT_OPTIONS, ...options };
    
          // Ensure output path is absolute and normalized
          const workspaceRoot = getWorkspaceRoot();
          const outputPath = path.isAbsolute(mergedOptions.outputPath)
            ? mergedOptions.outputPath
            : path.join(workspaceRoot, mergedOptions.outputPath);
    
          mergedOptions.outputPath = outputPath;
    
          // Ensure output directory exists
          try {
            await fs.mkdir(outputPath, { recursive: true });
          } catch (mkdirError: any) {
            throw new Error(`Failed to create output directory: ${mkdirError.message}`);
          }
    
          const sessionId = ActionRecorder.getInstance().startSession();
    
          // Store options with the session
          const recorder = ActionRecorder.getInstance();
          const session = recorder.getSession(sessionId);
          if (session) {
            session.options = mergedOptions;
          }
    
          return {
            sessionId,
            options: mergedOptions,
            message: `Started codegen session. Tests will be generated in: ${outputPath}`,
          };
        } catch (error: any) {
          throw new Error(`Failed to start codegen session: ${error.message}`);
        }
      },
    };
  • Input schema definition for 'start_codegen_session' used in createToolDefinitions for MCP tool discovery.
    {
      name: "start_codegen_session",
      description: "Start a new code generation session to record Playwright actions",
      inputSchema: {
        type: "object",
        properties: {
          options: {
            type: "object",
            description: "Code generation options",
            properties: {
              outputPath: {
                type: "string",
                description: "Directory path where generated tests will be saved (use absolute path)",
              },
              testNamePrefix: {
                type: "string",
                description: "Prefix to use for generated test names (default: 'GeneratedTest')",
              },
              includeComments: {
                type: "boolean",
                description: "Whether to include descriptive comments in generated tests",
              },
            },
            required: ["outputPath"],
          },
        },
        required: ["options"],
      },
    },
  • Registration and dispatch logic for codegen tools including 'start_codegen_session' in the main tool call handler switch statement.
    switch (name) {
      case "start_codegen_session":
        return await handleCodegenResult(startCodegenSession.handler(args, { server }));
      case "end_codegen_session":
        return await handleCodegenResult(endCodegenSession.handler(args, { server }));
      case "get_codegen_session":
        return await handleCodegenResult(getCodegenSession.handler(args, { server }));
      case "clear_codegen_session":
        return await handleCodegenResult(clearCodegenSession.handler(args, { server }));
    }
  • Import statement registering the startCodegenSession tool from codegen/index.ts into the main toolHandler.
    clearCodegenSession,
    endCodegenSession,
    getCodegenSession,
    startCodegenSession,
  • Export of codegenTools array including startCodegenSession for registration.
    export const codegenTools = [startCodegenSession, endCodegenSession, getCodegenSession, clearCodegenSession];
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool starts a session to record actions, implying a stateful, write-like operation, but doesn't describe what 'recording' entails (e.g., does it capture all subsequent actions automatically?), whether it requires specific permissions, if it has side effects like creating files, or what happens on failure. This leaves significant gaps for a tool that likely initiates a complex process.

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, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded with the core action ('Start a new code generation session') and specifies the outcome ('to record Playwright actions'), making it easy to parse. Every part of the sentence earns its place by conveying essential information.

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 complexity of starting a code generation session (likely a stateful, write operation with nested parameters) and the absence of both annotations and an output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., a session ID, success status), behavioral details like error handling, or how it interacts with sibling tools (e.g., 'clear_codegen_session'). For a tool with no structured safety or output information, more descriptive context is needed.

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 has 100% description coverage, documenting all parameters (options, outputPath, testNamePrefix, includeComments) with clear descriptions. The tool description adds no additional parameter semantics beyond what's in the schema, such as explaining how options affect recording behavior or providing examples. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't compensate but also doesn't detract.

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 the verb ('Start') and resource ('new code generation session') with the specific purpose 'to record Playwright actions'. It distinguishes from obvious siblings like 'end_codegen_session' and 'get_codegen_session' by indicating this initiates a session rather than terminating or retrieving one. However, it doesn't explicitly differentiate from all sibling tools that might also involve code generation or recording.

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., whether a session must be active or not), when to prefer this over other session-related tools, or what happens if multiple sessions are started. The context is implied through the name 'start' but lacks explicit usage instructions.

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/aakashH242/mcp-playwright'

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