Skip to main content
Glama

start_recording

Begin recording Android device interactions to create reusable automation macros. Capture subsequent tool calls for automated task execution.

Instructions

Start recording actions to create a macro. All subsequent tool calls will be recorded. Use stop_recording to save.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesName for this recording
device_idNoDevice serial numberdefault

Implementation Reference

  • The actual implementation of the startRecording logic that generates a UUID and initializes a new recording session.
    startRecording(name: string, deviceId: string): string {
      const id = uuidv4();
      const recording: Recording = {
        id,
        name,
        deviceId,
        createdAt: Date.now(),
        actions: [],
        metadata: {},
      };
    
      this.activeRecordings.set(id, recording);
      log.info('Recording started', { id, name, deviceId });
      return id;
    }
  • Registration of the 'start_recording' MCP tool, which calls the actionRecorder.startRecording method.
    server.registerTool(
      'start_recording',
      {
        description: 'Start recording actions to create a macro. All subsequent tool calls will be recorded. Use stop_recording to save.',
        inputSchema: {
          name: z.string().describe('Name for this recording'),
          device_id: z.string().optional().default('default').describe('Device serial number'),
        },
      },
      async ({ name, device_id }) => {
        const id = actionRecorder.startRecording(name, device_id || 'default');
        return {
          content: [{
            type: 'text' as const,
            text: JSON.stringify({ success: true, recording_id: id, name }, null, 2),
          }],
        };
      }
    );
Behavior4/5

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

With no annotations provided, the description carries full burden and adequately discloses key behaviors: it explains the stateful nature (recording starts and persists), the capture scope (subsequent calls), and the persistence mechanism (requires stop_recording to save). Minor gap: doesn't mention what happens if called twice or session ends prematurely.

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?

Three sentences, zero waste. Front-loaded with the core action, followed by mechanism scope, and closed with the explicit next step. Every sentence earns its place with no redundant or tangential information.

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

Completeness4/5

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

Adequately complete for a stateful recording tool with no output schema. Covers initiation, operation scope, and termination workflow. Minor gap: doesn't specify what the immediate return value indicates (success confirmation?), but the functional behavior is fully documented.

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 coverage is 100% with clear descriptions for both 'name' and 'device_id'. The description appropriately focuses on behavioral context rather than repeating parameter details that are well-documented in the schema. Baseline 3 is correct when schema provides complete coverage.

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 specific action ('Start recording actions') and resource ('macro') clearly. Explicitly distinguishes from sibling 'stop_recording' by stating this initiates the process while stop_recording saves, and differentiates from capture_screenshot/replay_recording by emphasizing the action-recording nature.

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?

Provides explicit workflow guidance: 'All subsequent tool calls will be recorded' establishes the scope, and 'Use stop_recording to save' explicitly names the complementary tool needed to complete the operation, establishing clear when-to-use boundaries.

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/divineDev-dotcom/android_mcp'

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