Skip to main content
Glama

Think Reset

think_reset

Clear the current thinking session to start fresh with a new problem when previous reasoning becomes irrelevant.

Instructions

Clear thinking session and start fresh.

Use when:

  • Starting a NEW problem

  • Previous chain is irrelevant

⚠️ Irreversible. All thoughts will be lost. Note: Auto-resets on thought #1.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • src/index.ts:374-385 (registration)
    Registration of the 'think_reset' MCP tool, including empty input schema and inline handler that delegates to ThinkingService.resetSession() and returns formatted success/error response.
    server.registerTool('think_reset', { title: 'Think Reset', description: THINK_RESET_DESCRIPTION, inputSchema: {} },
      async () => {
        try {
          const result = await thinkingService.resetSession();
          return {
            content: [{ type: 'text' as const, text: `🧹 RESET: ${result.clearedThoughts} thoughts, ${result.clearedBranches} branches cleared` }],
          };
        } catch (error) {
          return { content: [{ type: 'text' as const, text: `Error: ${error instanceof Error ? error.message : 'Unknown'}` }], isError: true };
        }
      }
    );
  • Core implementation of session reset: captures counts, clears in-memory state via reset(), deletes persistent session file via clearSession(), logs and returns cleared counts.
    async resetSession(): Promise<{ clearedThoughts: number; clearedBranches: number }> {
      const clearedThoughts = this.thoughtHistory.length;
      const clearedBranches = this.branches.size;
    
      this.reset();
      await this.clearSession();
    
      console.error(`🧹 Session reset: cleared ${clearedThoughts} thoughts, ${clearedBranches} branches`);
    
      return { clearedThoughts, clearedBranches };
    }
  • Private reset method that clears all in-memory session state: thought history, branches, counters, goal, session ID, coaching cooldown, and dead ends.
    reset(): void {
      this.thoughtHistory = [];
      this.branches.clear();
      this.lastThoughtNumber = 0;
      this.sessionGoal = undefined; // Clear goal on reset (v2.10.0)
      this.currentSessionId = ''; // Clear sessionId on reset (v2.11.0)
      this.coachingService.reset(); // Clear coach cooldown (v3.2.0)
      this.deadEnds = []; // Clear dead ends (v3.3.0)
    }
Behavior4/5

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

With no annotations provided, the description carries full burden. It discloses key behavioral traits: the irreversible nature ('⚠️ Irreversible. All thoughts will be lost') and the auto-reset condition. However, it doesn't mention potential side effects like session state changes or error conditions, leaving some behavioral aspects uncovered.

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 perfectly structured and concise: a clear purpose statement, bulleted usage guidelines, a warning, and a note. Every sentence earns its place with no wasted words, and information is front-loaded with the core action first.

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?

For a parameterless tool with no annotations or output schema, the description provides strong contextual completeness: purpose, usage guidelines, and behavioral warnings. The only minor gap is lack of explicit mention about what happens after reset (e.g., empty session state), but the 'start fresh' implication is reasonably clear.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage. The description appropriately doesn't discuss parameters, maintaining focus on the tool's purpose and behavior. This meets expectations for a parameterless tool, though it doesn't add semantic value beyond the schema (which is fine given no parameters exist).

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 clearly states the tool's purpose with specific verbs ('Clear thinking session and start fresh'), distinguishing it from siblings like 'think' (add thoughts), 'think_batch' (batch add), 'think_done' (end session), and 'think_recall' (retrieve thoughts). It precisely identifies the resource (thinking session) and action (reset).

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?

Explicit usage guidelines are provided: 'Use when: - Starting a NEW problem - Previous chain is irrelevant'. This clearly states when to use this tool versus continuing with existing thoughts, and the 'Note: Auto-resets on thought #1' offers additional context about default behavior, though it doesn't name specific alternatives.

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/GofMan5/think-mcp'

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