Skip to main content
Glama
davidorex

Project Handoffs MCP Server

by davidorex

start_working_session

Begin working on a specific next step within a project to facilitate task handoffs and maintain workflow continuity.

Instructions

Start working on a next step

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectIdYesProject identifier
nextStepIdYesID of the next step to work on

Implementation Reference

  • Core handler function in ProjectManager class that validates the next step, updates its status to 'in-progress', creates a new WorkingSession, saves the project data, and returns the session.
    async startWorkingSession(projectId: string, nextStepId: string): Promise<WorkingSession> {
      const data = await this.loadProjectData(projectId);
      
      const step = data.nextSteps.find(s => s.id === nextStepId);
      if (!step) {
        throw new ProjectError(`Next step not found: ${nextStepId}`, projectId);
      }
      if (step.status !== 'open') {
        throw new ProjectError(`Next step is not open: ${nextStepId}`, projectId);
      }
      
      step.status = 'in-progress';
      step.lastModified = new Date().toISOString();
    
      const session: WorkingSession = {
        id: `session_${Date.now()}`,
        nextStepId,
        startTime: new Date().toISOString(),
        progressNotes: [],
        blockers: [],
        decisions: []
      };
    
      data.workingSessions.push(session);
      await this.saveProjectData(projectId, data);
      return session;
    }
  • src/index.ts:346-357 (registration)
    Tool registration in the ListTools response, defining name, description, and input schema.
    {
      name: "start_working_session",
      description: "Start working on a next step",
      inputSchema: {
        type: "object",
        properties: {
          projectId: { type: "string", description: "Project identifier" },
          nextStepId: { type: "string", description: "ID of the next step to work on" }
        },
        required: ["projectId", "nextStepId"]
      }
    },
  • Dispatch handler in CallToolRequestSchema that invokes the ProjectManager.startWorkingSession method and formats the response.
    case "start_working_session":
      const session = await projectManager.startWorkingSession(
        args.projectId as string,
        args.nextStepId as string
      );
      return {
        content: [{
          type: "text",
          text: JSON.stringify(session, null, 2)
        }]
      };
  • Input schema definition specifying required projectId and nextStepId parameters.
    inputSchema: {
      type: "object",
      properties: {
        projectId: { type: "string", description: "Project identifier" },
        nextStepId: { type: "string", description: "ID of the next step to work on" }
      },
      required: ["projectId", "nextStepId"]
    }
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure but is insufficient. 'Start working' implies a state change or mutation, but it doesn't specify if this requires authentication, affects other data (e.g., locking the step), has side effects, or what the expected outcome is (e.g., returns a session ID). Critical behavioral traits are missing.

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 a single, efficient sentence with no wasted words, making it appropriately concise. However, it's under-specified rather than optimally structured—it could be more front-loaded with key details, but it avoids redundancy and is easy to parse.

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 the complexity of a state-changing tool with no annotations and no output schema, the description is incomplete. It doesn't explain what 'starting work' means operationally, what the tool returns, or how it interacts with the system (e.g., is it idempotent?). For a mutation tool, this lack of context is a significant gap.

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?

The schema description coverage is 100%, with clear parameter descriptions ('Project identifier' and 'ID of the next step to work on'), so the baseline is 3. The description adds no additional meaning beyond the schema, such as explaining how 'nextStepId' relates to other tools or what constitutes a valid ID, but it doesn't need to compensate for gaps.

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

Purpose2/5

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

The description 'Start working on a next step' is vague and tautological—it essentially restates the tool name 'start_working_session' without specifying what 'working' entails (e.g., initiating a timer, logging activity, or updating status). It fails to distinguish this tool from siblings like 'get_next_step_history' or 'create_next_step', leaving the agent unclear about its specific function.

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. For instance, it doesn't clarify if this should be used before 'create_next_step' or after 'get_latest_next_steps', nor does it mention prerequisites like needing an existing project or next step. The description offers no context for selection among sibling tools.

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/davidorex/project-handoffs'

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