Skip to main content
Glama

create_research_template

Generate structured research templates to document findings systematically, supporting organized analysis and decision records.

Instructions

Create a research template file for documenting findings

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesTitle of the research
categoryNoResearch categorygeneral
researchPathNoPath to research directorydocs/research

Implementation Reference

  • Main MCP tool handler for 'create_research_template'. Validates input, imports helper to generate template, creates filename, and returns structured response with template content and next steps.
    export async function createResearchTemplate(args: {
      title?: string;
      projectPath?: string;
      researchType?: string;
      category?: string;
      researchPath?: string;
      includeProjectAnalysis?: boolean;
    }): Promise<any> {
      const {
        title = args.researchType || 'Research Template',
        projectPath: _projectPath = '/project',
        researchType = 'general',
        category = researchType || 'general',
        researchPath = 'docs/research',
        includeProjectAnalysis: _includeProjectAnalysis = false,
      } = args;
    
      try {
        // Validate title parameter
        if (!title || typeof title !== 'string') {
          throw new Error('Title is required and must be a string');
        }
    
        const { createResearchTemplate } = await import('../utils/research-integration.js');
    
        const template = createResearchTemplate(title, category);
        const filename = `${title
          .toLowerCase()
          .replace(/[^a-z0-9\s-]/g, '')
          .replace(/\s+/g, '-')}.md`;
        const fullPath = `${researchPath}/${filename}`;
    
        return {
          content: [
            {
              type: 'text',
              text: `# Research Template Created
    
    ## Template Details
    - **Title**: ${title}
    - **Category**: ${category}
    - **Filename**: ${filename}
    - **Full Path**: ${fullPath}
    
    ## Template Content
    
    \`\`\`markdown
    ${template}
    \`\`\`
    
    ## Next Steps
    
    1. **Save the template** to the specified path: \`${fullPath}\`
    2. **Fill in the research details** following the template structure
    3. **Conduct your research** and document findings
    4. **Use the research integration tool** to analyze impact on ADRs
    
    ## Template Sections
    
    - **Research Question**: Define what you're investigating
    - **Background**: Provide context and motivation
    - **Methodology**: Describe your research approach
    - **Key Findings**: Document specific discoveries with evidence
    - **Implications**: Analyze architectural and technology impact
    - **Recommendations**: Provide actionable suggestions
    - **Related ADRs**: Link to potentially affected decisions
    - **Next Steps**: Plan follow-up actions
    
    ## Research Best Practices
    
    - Use clear, specific research questions
    - Document evidence and sources thoroughly
    - Assess confidence levels for findings
    - Consider architectural implications early
    - Link findings to existing ADRs when relevant
    - Plan for regular research reviews and updates
    `,
            },
          ],
        };
      } catch (error) {
        throw new McpAdrError(
          `Failed to create research template: ${error instanceof Error ? error.message : String(error)}`,
          'TEMPLATE_CREATION_ERROR'
        );
      }
    }
  • Supporting utility function that generates the actual Markdown template content for research documents based on title and category.
    export function createResearchTemplate(title: string, category: string = 'general'): string {
      const date = new Date().toISOString().split('T')[0];
    
      return `# ${title}
    
    **Date**: ${date}
    **Category**: ${category}
    **Status**: In Progress
    
    ## Research Question
    
    [What specific question or problem is this research addressing?]
    
    ## Background
    
    [Provide context and background information]
    
    ## Methodology
    
    [Describe how the research was conducted]
    
    ## Key Findings
    
    ### Finding 1
    - **Description**: [Detailed description]
    - **Evidence**: [Supporting evidence or data]
    - **Confidence**: [High/Medium/Low]
    - **Source**: [Source of information]
    
    ### Finding 2
    - **Description**: [Detailed description]
    - **Evidence**: [Supporting evidence or data]
    - **Confidence**: [High/Medium/Low]
    - **Source**: [Source of information]
    
    ## Implications
    
    ### Architectural Impact
    [How do these findings impact architectural decisions?]
    
    ### Technology Choices
    [What technology choices are affected?]
    
    ### Risk Assessment
    [What risks are identified or mitigated?]
    
    ## Recommendations
    
    1. [Specific recommendation 1]
    2. [Specific recommendation 2]
    3. [Specific recommendation 3]
    
    ## Related ADRs
    
    - [List any ADRs that might be affected by this research]
    
    ## Next Steps
    
    - [ ] [Action item 1]
    - [ ] [Action item 2]
    - [ ] [Action item 3]
    
    ## References
    
    - [Reference 1]
    - [Reference 2]
    - [Reference 3]
    `;
  • TypeScript type definition for the tool input parameters (schema). Defines optional parameters like title, category, paths, etc.
    export async function createResearchTemplate(args: {
      title?: string;
      projectPath?: string;
      researchType?: string;
      category?: string;
      researchPath?: string;
      includeProjectAnalysis?: boolean;
    }): Promise<any> {
  • Tool listed in server context generator's hardcoded tool catalog, indicating availability and description.
    name: 'create_research_template',
    description: 'Create structured research templates for investigations',
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. It states 'create' which implies a write operation, but doesn't disclose behavioral traits like what permissions are needed, whether it overwrites existing files, what format the template uses, or what happens on failure. For a creation tool with zero annotation coverage, 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.

Conciseness5/5

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

The description is a single, efficient sentence that gets straight to the point with no wasted words. It's appropriately sized for a simple creation tool and front-loads the essential information.

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?

For a creation tool with no annotations and no output schema, the description is too minimal. It doesn't explain what the created template contains, how it's structured, what happens if the path doesn't exist, or what the tool returns. Given the complexity of file creation and the lack of structured data, more context is needed.

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 three parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema. With complete schema coverage, the baseline of 3 is appropriate as the description doesn't compensate but also doesn't need to.

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 action ('create') and resource ('research template file for documenting findings'), making the purpose immediately understandable. It doesn't distinguish from siblings like 'write_file' or 'generate_research_questions', but provides a specific enough purpose without being tautological.

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 is provided on when to use this tool versus alternatives like 'write_file' or 'generate_research_questions' from the sibling list. The description only states what it does, not when it's appropriate or what prerequisites might exist.

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/tosin2013/mcp-adr-analysis-server'

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