Skip to main content
Glama
coderdeep11

Claude Infinite Context

by coderdeep11

status

Check current project state including version, active files, tasks, token usage, and checkpoint history to monitor progress and manage long-term context.

Instructions

Show current state metadata including version, active files, tasks, token usage, and checkpoint history.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Core handler function that retrieves project state and checkpoint history from Redis, formats a detailed status report including session info, metadata, active files, decisions, and history.
    async status(): Promise<string> {
      const sessionId = this.ensureInitialized();
    
      try {
        const state = await this.redis.getState(sessionId);
        const history = await this.redis.getCheckpointHistory(sessionId);
    
        const sections: string[] = [];
    
        sections.push('# Project State Status');
        sections.push('');
        sections.push(`Session ID: ${sessionId}`);
        sections.push(`Version: ${state.meta.version}`);
        sections.push(
          `Last Checkpoint: ${new Date(state.meta.last_checkpoint).toLocaleString()}`
        );
        sections.push(
          `Last Access: ${new Date(state.meta.last_access).toLocaleString()}`
        );
        sections.push(
          `Token Budget Used: ${state.meta.token_budget_used.toLocaleString()} / 200,000 (${(
            (state.meta.token_budget_used / 200000) *
            100
          ).toFixed(1)}%)`
        );
        sections.push('');
    
        sections.push(`Active Files: ${state.active_context.active_files.length}`);
        state.active_context.active_files.forEach((file) => {
          sections.push(`  - ${file}`);
        });
        sections.push('');
    
        sections.push(`Active Decisions: ${state.active_context.active_decisions.length}`);
        state.active_context.active_decisions.forEach((decision) => {
          sections.push(`  - [${decision.status}] ${decision.question}`);
        });
        sections.push('');
    
        sections.push(`Checkpoint History: ${history.length} versions available`);
        history.forEach((h, i) => {
          sections.push(
            `  ${i}. v${h.version} - ${new Date(h.timestamp).toLocaleString()} (${h.merge_duration_ms
            }ms, ${h.token_count} tokens)`
          );
        });
    
        return sections.join('\n');
      } catch (error) {
        logger.error('Status check failed', { error, sessionId });
        throw new Error(`Status check failed: ${error}`);
      }
    }
  • src/index.ts:100-108 (registration)
    Tool registration in the MCP ListToolsRequestHandler, defining the 'status' tool name, description, and empty input schema.
    {
      name: 'status',
      description:
        'Show current state metadata including version, active files, tasks, token usage, and checkpoint history.',
      inputSchema: {
        type: 'object',
        properties: {},
      },
    },
  • Dispatch handler in the main CallToolRequestSchema handler that invokes ProjectBrain.status() and formats the MCP response.
    case 'status': {
      const result = await this.brain.status();
      return {
        content: [{ type: 'text', text: result }],
      };
    }
Behavior3/5

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

With no annotations provided, the description carries full burden. It clearly indicates this is a read-only operation ('Show') and specifies what information will be returned, but doesn't disclose behavioral traits like whether it requires authentication, has rate limits, or how frequently the state updates. The description adds value by listing the metadata components but lacks operational context.

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 front-loads the core purpose ('Show current state metadata') followed by specific examples. Every word earns its place by either stating the action or enumerating the metadata components without unnecessary elaboration or repetition.

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 tool's zero-parameter simplicity and lack of both annotations and output schema, the description provides adequate but minimal context. It tells what information will be shown but doesn't explain format, structure, or potential limitations of the returned metadata. For a status monitoring tool with no structured output definition, more detail about the return values would be helpful.

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 zero parameters with 100% schema description coverage, so the baseline is 4. The description appropriately doesn't discuss parameters since none exist, focusing instead on what the tool returns. No parameter information is needed or provided beyond what the schema already indicates.

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 specific action ('Show') and the comprehensive scope of resources ('current state metadata including version, active files, tasks, token usage, and checkpoint history'). It effectively distinguishes from siblings like checkpoint, resume, and rollback by focusing on read-only status display rather than state manipulation.

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

Usage Guidelines3/5

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

The description implies usage context through the listed metadata items, suggesting it's for monitoring system state. However, it doesn't explicitly state when to use this tool versus alternatives like checking specific resources individually, nor does it mention any prerequisites or exclusions for usage.

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/coderdeep11/claude-memory-mcp'

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