Skip to main content
Glama
rodhayl
by rodhayl

mcp_plan_implementation

Convert feature requests into actionable implementation steps by analyzing requirements and codebase context to generate structured development plans.

Instructions

Turn a feature request into concrete implementation steps.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
featureYesFeature description or requirement
codebaseNoBrief description of existing codebase (optional)
constraintsNoTechnical constraints (optional)

Implementation Reference

  • The implementation of the `mcp_plan_implementation` tool handler inside `CodeAssistanceTools.planImplementation`. It uses the `toolLlmWrapper` to execute the planning logic.
      async planImplementation(
        taskDescription: string,
        options?: {
          codebaseContext?: string;
          existingFiles?: string[];
          constraints?: string[];
        }
      ): Promise<PlanImplementationResult> {
        const prompt = `You are an expert software architect. Create a step-by-step implementation plan for the following task.
    
    ${options?.codebaseContext ? `Codebase context:\n${options.codebaseContext}` : ''}
    ${options?.existingFiles ? `Existing files to consider:\n${options.existingFiles.join('\n')}` : ''}
    ${options?.constraints ? `Constraints:\n${options.constraints.join('\n')}` : ''}
    
    Provide your response as JSON:
    {
      "plan": [
        {
          "step": 1,
          "title": "Step title",
          "description": "Detailed description",
          "files": ["files to modify or create"],
          "estimatedEffort": "small|medium|large",
          "dependencies": [0]
        }
      ],
      "summary": "Overall summary of the plan",
      "estimatedTotalEffort": "Total time estimate",
      "risks": ["Potential risks or challenges"]
    }`;
    
        try {
          const responseText = await this.llmWrapper.callToolLlm(
            'mcp_plan_implementation',
            [
              { role: 'system', content: prompt },
              { role: 'user', content: `Task: ${taskDescription}` },
            ],
            { type: 'plan_implementation' }
          );
    
          const parsed = this.parseJsonResponse(responseText, {
            plan: [],
            summary: responseText,
            estimatedTotalEffort: 'Unknown',
          });
    
          return {
            success: true,
            plan: parsed.plan || [],
            summary: parsed.summary || '',
            estimatedTotalEffort: parsed.estimatedTotalEffort || 'Unknown',
            risks: parsed.risks,
          };
        } catch (error) {
          return {
            success: false,
            plan: [],
            summary: '',
            estimatedTotalEffort: '',
            error: error instanceof Error ? error.message : 'Unknown error',
          };
        }
      }
  • Schema definition for the result of `planImplementation`.
    export interface PlanImplementationResult {
      success: boolean;
      plan: Array<{
        step: number;
        title: string;
        description: string;
        files?: string[];
        estimatedEffort?: 'small' | 'medium' | 'large';
        dependencies?: number[];
      }>;
      summary: string;
      estimatedTotalEffort: string;
      risks?: string[];
      error?: string;
    }
Behavior2/5

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

No annotations are provided, so the description carries full disclosure burden. While it states the transformation intent, it fails to clarify whether this creates/modifies files (destructive) or returns analysis (read-only), what format the steps take, or failure modes for vague feature descriptions.

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?

Single sentence of seven words. The action and resource are front-loaded. No redundancy or filler content—every word earns its place.

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?

With no output schema and no annotations, the description must compensate by describing the output format and side effects. It does neither. Additionally, given the crowded sibling namespace of code tools, it should clarify that this outputs a plan rather than implements code.

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 coverage is 100%, establishing a baseline of 3. The description mentions 'feature request' which aligns with the 'feature' parameter, but adds no syntax details, format constraints, or semantic relationships between parameters (e.g., how constraints affect the planning) beyond what the schema already provides.

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 uses a specific verb ('Turn') and identifies both the input resource ('feature request') and output ('concrete implementation steps'). However, it does not differentiate from sibling tools like code_helper, draft_file, or refactor_helper that might also generate implementation content.

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 provided on when to use this tool versus alternatives like code_helper or draft_file. No mention of prerequisites, constraints, or when this planning approach is preferred over direct implementation suggestions.

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/rodhayl/mcpLocalHelper'

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