Skip to main content
Glama
anortham

COA Goldfish MCP

by anortham

checkpoint

Save your progress and session state by creating a checkpoint. Track files, branch, and highlights to ensure crash-safe development and maintain context across workspaces.

Instructions

Create a checkpoint to save current progress. Use frequently for crash-safe development. Required: description only. Optional: add context like files, branch, highlights for detailed session tracking.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
activeFilesNoFiles currently being worked on
descriptionYesBrief description of what was accomplished or current state
gitBranchNoCurrent git branch (auto-detected if not provided)
globalNoStore as global checkpoint (visible across all workspaces)
highlightsNoImportant achievements or decisions to remember (accumulates in session)
sessionIdNoSession identifier (auto-generated if not provided)
workContextNoWhat you were working on or next steps
workspaceNoStore in specific workspace (default: current workspace)

Implementation Reference

  • Main entry point for the 'checkpoint' tool. Infers the action (save, restore, search, timeline) from arguments and dispatches to the appropriate private handler method.
    async handleUnifiedCheckpoint(args: UnifiedCheckpointArgs): Promise<ToolResponse> {
      try {
        // Determine action - use provided action or infer from arguments
        const action = args.action || inferCheckpointAction(args);
        
        // Route to appropriate handler based on action
        switch (action) {
          case 'save':
            return this.handleSave(args);
          case 'restore':
            return this.handleRestore(args);
          case 'search':
            return this.handleSearch(args);
          case 'timeline':
            return this.handleTimeline(args);
          default:
            return {
              content: [
                {
                  type: 'text',
                  text: `❓ Unknown action: ${action}. Supported actions: save, restore, search, timeline`
                }
              ]
            };
        }
        
      } catch (error) {
        return {
          content: [
            {
              type: 'text',
              text: `❌ Error in checkpoint tool: ${error instanceof Error ? error.message : 'Unknown error'}`
            }
          ]
        };
      }
    }
  • Defines the MCP tool schema for 'checkpoint' including name, description, and comprehensive inputSchema with all parameters for different actions (save, restore, search, timeline).
    static getToolSchema() {
      return {
        name: 'checkpoint',
        description: 'Save progress or restore session context. Use after completing tasks, before breaks, when resuming work, or asking "what was I working on?"',
        inputSchema: {
          type: 'object',
          properties: {
            action: {
              type: 'string',
              enum: ['save', 'restore', 'search', 'timeline'],
              description: 'Action to perform. Defaults to "restore" (most common). Use "save" with description to create checkpoint.'
            },
            
            // Save action properties
            description: {
              type: 'string',
              description: 'Checkpoint description (required for save action)'
            },
            highlights: {
              type: 'array',
              items: { type: 'string' },
              description: 'Key achievements or decisions to remember'
            },
            activeFiles: {
              type: 'array',
              items: { type: 'string' },
              description: 'Files currently being worked on'
            },
            gitBranch: {
              type: 'string',
              description: 'Current git branch (auto-detected if not provided)'
            },
            workContext: {
              type: 'string',
              description: 'What you\'re working on or next steps'
            },
            sessionId: {
              type: 'string',
              description: 'Session identifier (auto-generated if not provided)'
            },
            global: {
              type: 'boolean',
              description: 'Store as global checkpoint (visible across all workspaces)',
              default: false
            },
            
            // Restore action properties
            checkpointId: {
              type: 'string',
              description: 'Specific checkpoint ID to restore'
            },
            depth: {
              type: 'string',
              enum: ['minimal', 'highlights', 'full'],
              description: 'Restoration depth',
              default: 'highlights'
            },
            mode: {
              type: 'string',
              enum: ['latest', 'specific', 'search'],
              description: 'Restoration mode',
              default: 'latest'
            },
            
            // Search action properties
            query: {
              type: 'string',
              description: 'Search query for finding specific checkpoints'
            },
            since: {
              type: 'string',
              description: 'Time range for search (e.g., "24h", "1week")'
            },
            limit: {
              type: 'number',
              description: 'Maximum number of results to return',
              default: 10
            },
            
            // Timeline action properties
            range: {
              type: 'string',
              description: 'Time range for timeline: "1h", "24h", "7d", "30d"',
              default: '7d'
            },
            format: {
              type: 'string',
              enum: ['compact', 'detailed'],
              description: 'Timeline display format',
              default: 'compact'
            },
            
            // Common properties
            workspace: {
              type: 'string',
              description: 'Target workspace (path or name)'
            },
            outputFormat: {
              type: 'string',
              enum: ['plain', 'emoji', 'json', 'dual'],
              description: 'Output format override'
            }
          }
        }
      };
    }
  • Registers the 'checkpoint' tool handler in the MCP server's CallToolRequestSchema handler by dispatching to UnifiedCheckpointTool.handleUnifiedCheckpoint
    case 'checkpoint':
      return await this.unifiedCheckpointTool.handleUnifiedCheckpoint(args as any);
  • Registers the 'checkpoint' tool schema in the MCP server's ListToolsRequestSchema response
    // Unified checkpoint tool (replaces checkpoint, restore_session, and search functionality)
    UnifiedCheckpointTool.getToolSchema(),
  • Helper function that intelligently infers the checkpoint action based on provided arguments, enabling flexible usage without explicit action specification.
    function inferCheckpointAction(args: UnifiedCheckpointArgs): 'save' | 'restore' | 'search' | 'timeline' {
      // If we have description, it's a save (checkpoint creation)
      if (args.description) {
        return 'save';
      }
      
      // If we have query, it's a search
      if (args.query) {
        return 'search';
      }
      
      // If we have range, it's a timeline
      if (args.range) {
        return 'timeline';
      }
      
      // If we have checkpointId or depth specified, it's a restore
      if (args.checkpointId || args.depth || args.mode) {
        return 'restore';
      }
      
      // Default to restore (most common operation)
      return 'restore';
    }
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'save current progress' and 'session tracking,' which implies data persistence, but doesn't specify where checkpoints are stored, their retention policy, or whether they're reversible. It hints at accumulation ('accumulates in session') but lacks details on how checkpoints relate to each other. For a tool with mutation implications and no annotations, this is insufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately concise with three sentences. It front-loads the core purpose, then provides usage advice and parameter guidance. No wasted words, though it could be slightly more structured (e.g., bullet points for parameters).

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 complexity (8 parameters, mutation operation) and lack of annotations/output schema, the description is moderately complete. It covers the basic purpose and usage but misses key behavioral details like storage mechanism, error handling, or what 'create' actually does (e.g., returns a checkpoint ID). It's adequate but has clear gaps for a tool that saves state.

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 description coverage is 100%, so the schema already documents all 8 parameters thoroughly. The description adds minimal value: it notes 'description' is required and lists 'context like files, branch, highlights' as optional examples, but doesn't explain parameter interactions or semantics beyond what's in the schema. This meets the baseline for high schema coverage.

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 tool's purpose: 'Create a checkpoint to save current progress.' It specifies the verb ('create') and resource ('checkpoint'), but doesn't explicitly differentiate from siblings like 'restore_session' or 'search_history' that might involve checkpoints. The mention of 'crash-safe development' adds useful context about the primary use case.

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 provides some usage guidance: 'Use frequently for crash-safe development' suggests when to use it, and 'Required: description only' clarifies the minimal requirement. However, it doesn't explicitly state when NOT to use it or mention alternatives among the sibling tools (e.g., vs. 'remember' or 'summarize_session'). The guidance is implied rather than explicit.

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/anortham/coa-goldfish-mcp'

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