Skip to main content
Glama
core3-coder

Context Continuation MCP Server

by core3-coder

context_log_decision

Track and document technical decisions by logging project context, alternatives, consequences, and status to maintain clarity and continuity in AI development processes.

Instructions

Log a technical decision

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
alternativesNoAlternative options considered
consequencesNoConsequences of the decision
contextNoDecision context
decisionYesThe decision made
projectPathYesPath to project directory
statusNoDecision statusaccepted
titleYesDecision title

Implementation Reference

  • The core handler function that logs a technical decision by appending a formatted markdown entry to the decisions.md file in the project's .context/progress directory. This implements the logic for the 'context_log_decision' tool.
    async logDecision(projectPath: string, decision: Omit<TechnicalDecision, 'id' | 'createdAt'>): Promise<void> {
      const decisionsPath = path.join(projectPath, '.context', 'progress', 'decisions.md');
      
      const newDecision: TechnicalDecision = {
        ...decision,
        id: this.generateId(),
        createdAt: new Date(),
      };
    
      await this.ensureProgressDirectory(projectPath);
      
      let content = '';
      try {
        content = await fs.readFile(decisionsPath, 'utf8');
      } catch {
        content = '# Technical Decisions\n\n';
      }
    
      const decisionMarkdown = this.generateDecisionMarkdown(newDecision);
      content += `\n${decisionMarkdown}\n`;
    
      await fs.writeFile(decisionsPath, content, 'utf8');
    }
  • Type definition/schema for the technical decision object used as input to the logDecision handler.
    export interface TechnicalDecision {
      id: string;
      title: string;
      context: string;
      decision: string;
      alternatives: string[];
      consequences: string[];
      status: 'proposed' | 'accepted' | 'rejected';
      createdAt: Date;
    }
  • Helper function that formats a TechnicalDecision into markdown for storage in decisions.md.
      private generateDecisionMarkdown(decision: TechnicalDecision): string {
        const date = format(decision.createdAt, 'yyyy-MM-dd');
        
        return `### ADR-${this.generateId().slice(-3)}: ${decision.title}
    **Date:** ${date}  
    **Status:** ${decision.status}  
    **Context:** ${decision.context}  
    **Decision:** ${decision.decision}  
    **Consequences:** ${decision.consequences.join(', ')}`;
      }
Behavior2/5

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

No annotations are provided, so the description carries full burden but discloses minimal behavioral traits. It mentions logging but doesn't specify where (e.g., file, database), permissions needed, or effects (e.g., irreversible, append-only). This leaves gaps for a mutation tool with 7 parameters.

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 ('Log a technical decision') that is front-loaded and wastes no words. It's appropriately sized for the tool's purpose, though it could benefit from more detail.

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

Completeness2/5

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

Given complexity (7 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain return values, error handling, or behavioral context, leaving the agent with insufficient information for proper invocation beyond basic parameter filling.

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 parameters are well-documented in the schema. The description adds no meaning beyond the schema, such as explaining relationships between parameters (e.g., how 'alternatives' relate to 'decision'). Baseline 3 is appropriate given high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Log a technical decision' states a clear verb ('Log') and resource ('technical decision'), but it's vague about what logging entails (e.g., where it's stored, format). It doesn't distinguish from siblings like 'context_add_milestone' or 'context_track_message', which might involve similar logging actions.

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?

No guidance on when to use this tool versus alternatives is provided. The description lacks context about prerequisites, timing, or comparisons to sibling tools like 'context_add_milestone' for milestone tracking or 'context_track_message' for message logging.

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/core3-coder/context-continue-mcp'

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