Skip to main content
Glama
cyqlelabs

MCP Dual-Cycle Reasoner

by cyqlelabs

start_monitoring

Initiate metacognitive monitoring to track and analyze an agent's reasoning process, ensuring alignment with specified goals and initial beliefs for effective task execution.

Instructions

Start metacognitive monitoring of an agent's cognitive process

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
goalYesCurrent goal being pursued
initial_beliefsNoInitial beliefs about the task and environment

Implementation Reference

  • The execute function serving as the MCP tool handler for 'start_monitoring'. It retrieves the session engine, logs the start, calls startMonitoring on the engine with goal and initial beliefs, and returns a success message.
    execute: async (args, { log, session }) => {
      try {
        const sessionEngine = this.getSessionEngine(session);
        const sessionId = this.sessionIds.get(session);
    
        log.info('Starting metacognitive monitoring', {
          goal: args.goal,
          initialBeliefsCount: args.initial_beliefs.length,
          sessionId,
        });
    
        await sessionEngine.startMonitoring(args.goal, args.initial_beliefs);
    
        log.info('Monitoring started successfully');
        return `✅ Metacognitive monitoring started for goal: "${args.goal}" with ${args.initial_beliefs.length} initial beliefs`;
      } catch (error) {
        const errorMessage = error instanceof Error ? error.message : String(error);
        log.error('Failed to start monitoring', { error: errorMessage });
        throw new UserError(`Failed to start monitoring: ${errorMessage}`);
      }
    },
  • Zod schema defining input parameters for the start_monitoring tool: goal (required string), initial_beliefs (optional array of strings, defaults to []).
    parameters: z.object({
      goal: z.string().describe(DESCRIPTIONS.GOAL),
      initial_beliefs: z
        .array(z.string())
        .optional()
        .default([])
        .describe(DESCRIPTIONS.INITIAL_BELIEFS),
    }),
  • src/server.ts:236-236 (registration)
    Registration of the 'start_monitoring' tool on the FastMCP server inside addStartMonitoringTool method. The full tool object including handler and schema is defined here. The method is called from setupTools at line 224.
    this.server.addTool({
  • Core helper method in DualCycleEngine that implements the monitoring startup logic: initializes state, sets goal, resets counters, ensures semantic analyzer ready, and logs startup.
    async startMonitoring(initialGoal: string, initialBeliefs: string[] = []): Promise<void> {
      // Ensure semantic analyzer is ready before starting monitoring
      await this.ensureSemanticAnalyzerReady();
    
      this.isMonitoring = true;
      this.currentTrace = this.initializeTrace();
      this.currentTrace.goal = initialGoal;
      this.interventionCount = 0;
      this.accumulatedActions = [];
    
      console.log(chalk.blue('🧠 Dual-Cycle Engine: Metacognitive monitoring started'));
      console.log(chalk.gray(`Goal: ${initialGoal}`));
      console.log(chalk.gray(`Initial beliefs: ${initialBeliefs.length}`));
    }
Behavior3/5

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

Annotations cover basic hints (e.g., not read-only, not destructive), but the description adds some context by implying this initiates a monitoring process, which suggests ongoing behavior. However, it doesn't detail what 'metacognitive monitoring' entails operationally, such as how it interacts with other tools or what side effects occur, leaving gaps in behavioral understanding.

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, direct sentence that efficiently conveys the core action without any wasted words. It's front-loaded and appropriately sized for the tool's complexity, making it easy to parse quickly.

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?

Given the lack of an output schema and the abstract nature of 'metacognitive monitoring', the description is minimally adequate but incomplete. It doesn't explain what happens after starting monitoring, what outputs or states to expect, or how it integrates with sibling tools, leaving significant contextual gaps for the agent.

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?

With 100% schema description coverage, the input schema fully documents both parameters ('goal' and 'initial_beliefs'). The description adds no additional meaning or context about these parameters, such as how they influence monitoring or typical values, so it meets the baseline but doesn't enhance parameter understanding.

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 action ('Start metacognitive monitoring') and the target ('an agent's cognitive process'), providing a specific verb+resource combination. However, it doesn't explicitly differentiate this from sibling tools like 'stop_monitoring' or 'get_monitoring_status' beyond the obvious start/stop distinction, which keeps it from a perfect score.

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 like 'stop_monitoring' or 'configure_detection'. It lacks context about prerequisites, typical scenarios, or exclusions, leaving the agent with minimal usage direction beyond the tool's name.

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

Related 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/cyqlelabs/mcp-dual-cycle-reasoner'

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