Skip to main content
Glama
jakedx6

Helios-9 MCP Server

by jakedx6

get_team_productivity

Measure team productivity by analyzing task completion, collaboration, code quality, and other dimensions over a chosen time range.

Instructions

Analyze team productivity patterns and performance

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
team_membersNoSpecific team member IDs to analyze (optional)
project_idNoProject context for analysis (optional)
time_rangeNoTime range for analysismonth
productivity_dimensionsNoDimensions of productivity to measure

Implementation Reference

  • Main handler function for get_team_productivity tool. Parses input (team_members, project_id, time_range, productivity_dimensions), fetches team data, analyzes each requested productivity dimension (task_completion, collaboration, code_quality, documentation, mentoring, innovation), calculates an overall score, and returns insights with improvement suggestions.
    export const getTeamProductivity = requireAuth(async (args: any) => {
      const { team_members, project_id, time_range, productivity_dimensions } = GetTeamProductivitySchema.parse(args)
      
      logger.info('Analyzing team productivity', { team_members, project_id, time_range })
    
      // Get team data
      const teamData = await getTeamData(team_members, project_id, time_range)
      
      const productivity: any = {
        time_range,
        team_size: teamData.members.length,
        project_context: project_id,
        analyzed_at: new Date().toISOString(),
        dimensions: {}
      }
    
      // Analyze each productivity dimension
      for (const dimension of productivity_dimensions) {
        try {
          switch (dimension) {
            case 'task_completion':
              productivity.dimensions.task_completion = analyzeTaskCompletion(teamData)
              break
            case 'collaboration':
              productivity.dimensions.collaboration = analyzeCollaboration(teamData)
              break
            case 'code_quality':
              productivity.dimensions.code_quality = analyzeCodeQuality(teamData)
              break
            case 'documentation':
              productivity.dimensions.documentation = analyzeDocumentation(teamData)
              break
            case 'mentoring':
              productivity.dimensions.mentoring = analyzeMentoring(teamData)
              break
            case 'innovation':
              productivity.dimensions.innovation = analyzeInnovation(teamData)
              break
          }
        } catch (error) {
          logger.error(`Failed to analyze ${dimension}:`, error)
          productivity.dimensions[dimension] = { error: 'Analysis failed' }
        }
      }
    
      // Calculate overall productivity score
      productivity.overall_score = calculateOverallProductivityScore(productivity.dimensions)
      
      // Generate team insights
      productivity.insights = generateTeamInsights(productivity.dimensions, teamData)
      productivity.improvement_suggestions = generateImprovementSuggestions(productivity.dimensions)
    
      return productivity
    })
  • Zod schema defining input validation for get_team_productivity: optional team_members array, optional project_id, time_range enum (week/month/quarter) defaulting to 'month', and productivity_dimensions array of six options defaulting to task_completion and collaboration.
    const GetTeamProductivitySchema = z.object({
      team_members: z.array(z.string()).optional(),
      project_id: z.string().optional(),
      time_range: z.enum(['week', 'month', 'quarter']).default('month'),
      productivity_dimensions: z.array(z.enum(['task_completion', 'collaboration', 'code_quality', 'documentation', 'mentoring', 'innovation'])).default(['task_completion', 'collaboration'])
    })
  • Tool definition/registration object for get_team_productivity with name, description, and inputSchema (JSON Schema format) matching the Zod schema. Exported via analyticsInsightsTools and registered in src/index.ts.
    export const getTeamProductivityTool: MCPTool = {
      name: 'get_team_productivity',
      description: 'Analyze team productivity patterns and performance',
      inputSchema: {
        type: 'object',
        properties: {
          team_members: {
            type: 'array',
            items: { type: 'string' },
            description: 'Specific team member IDs to analyze (optional)'
          },
          project_id: {
            type: 'string',
            description: 'Project context for analysis (optional)'
          },
          time_range: {
            type: 'string',
            enum: ['week', 'month', 'quarter'],
            default: 'month',
            description: 'Time range for analysis'
          },
          productivity_dimensions: {
            type: 'array',
            items: {
              type: 'string',
              enum: ['task_completion', 'collaboration', 'code_quality', 'documentation', 'mentoring', 'innovation']
            },
            default: ['task_completion', 'collaboration'],
            description: 'Dimensions of productivity to measure'
          }
        }
      }
    }
  • Export mapping the string key 'get_team_productivity' to the getTeamProductivity handler function, which gets merged into allHandlers in src/index.ts and invoked by the CallToolRequestSchema handler.
    export const analyticsInsightsHandlers = {
      get_project_analytics: getProjectAnalytics,
      get_team_productivity: getTeamProductivity,
      get_workspace_health: getWorkspaceHealth,
      generate_custom_report: generateCustomReport
  • Supporting helper functions called by the getTeamProductivity handler: getTeamData (fetches team data - currently placeholder), dimension analyzers (each returning mock scores), calculateOverallProductivityScore (averages all dimension scores), and insight/suggestion generators.
    // Additional helper functions would be implemented here...
    async function getTeamData(teamMembers?: string[], projectId?: string, timeRange?: string): Promise<any> {
      return { members: [] } // Placeholder
    }
    
    function analyzeTaskCompletion(teamData: any): any {
      return { score: 85, trends: 'positive' } // Placeholder
    }
    
    function analyzeCollaboration(teamData: any): any {
      return { score: 72, interaction_frequency: 'high' } // Placeholder
    }
    
    function analyzeCodeQuality(teamData: any): any {
      return { score: 78, review_coverage: 85 } // Placeholder
    }
    
    function analyzeDocumentation(teamData: any): any {
      return { score: 65, coverage: 'medium' } // Placeholder
    }
    
    function analyzeMentoring(teamData: any): any {
      return { score: 60, active_relationships: 3 } // Placeholder
    }
    
    function analyzeInnovation(teamData: any): any {
      return { score: 70, new_ideas: 5 } // Placeholder
    }
    
    function calculateOverallProductivityScore(dimensions: any): number {
      const scores = Object.values(dimensions).map((d: any) => d.score).filter(s => typeof s === 'number')
      return scores.length > 0 ? Math.round(scores.reduce((sum: number, score: number) => sum + score, 0) / scores.length) : 0
    }
    
    function generateTeamInsights(dimensions: any, teamData: any): string[] {
      return ['Team showing strong collaboration patterns', 'Documentation practices need improvement']
    }
    
    function generateImprovementSuggestions(dimensions: any): string[] {
      return ['Implement pair programming sessions', 'Create documentation templates']
    }
Behavior2/5

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

With no annotations, the description must disclose behavioral traits. It only says 'analyze', which suggests a read operation, but does not confirm read-only nature, required permissions, or any side effects.

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

Conciseness2/5

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

The description is a single 4-word sentence, which is overly minimal for a tool with 4 parameters and no annotations. It sacrifices substance for brevity.

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 no output schema, the description should explain the return value or how the analysis is presented. It lacks this information, making it incomplete for effective use.

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% with descriptive parameter names and enums. The description adds no further meaning beyond the schema, so a baseline score of 3 is appropriate.

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 'Analyze team productivity patterns and performance' clearly states the tool's verb and resource (analyze productivity). However, it does not differentiate from sibling tools like 'get_project_analytics' or 'get_workspace_health' which also analyze performance metrics.

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. The description implies usage for productivity analysis but gives no context on prerequisites or exclusions.

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/jakedx6/helios9-MCP-Server'

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