Skip to main content
Glama

roadmap_view

View project roadmaps to track work status, identify pending or blocked tasks, and monitor progress across organizations and projects.

Instructions

PROJECT MANAGEMENT (TPM): Get project roadmap showing work status.

USE THIS TOOL WHEN:

  • User asks "what's in progress?" or "what are we working on?"

  • User asks "TPM status", ":TPM:" prefix, or "show me the roadmap"

  • User asks about pending/blocked/completed work

  • Starting a work session to see current state

  • User completes work and you need to find related tasks to mark done

Returns summary of organizations, projects, and tickets. Use project_id filter to reduce output.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
org_idNoFilter by organization ID (optional) case-insensitive
project_idNoFilter by project ID (optional) - recommended to reduce output size
active_onlyNoOnly show non-done tickets (default: true)

Implementation Reference

  • Handler logic for roadmap_view tool: fetches roadmap from DB, applies filters, formats as markdown summary.
    if name == "roadmap_view":
        roadmap = db.get_roadmap(args.get("org_id"))
        project_filter = args.get("project_id", "").lower() if args.get("project_id") else None
        active_only = args.get("active_only", True)
    
        # Summary format (always use summary now - json was too large)
        lines = ["# Roadmap Summary\n"]
        lines.append(
            f"**Stats**: {roadmap.stats['tickets_done']}/{roadmap.stats['total_tickets']} tickets, "
            f"{roadmap.stats['tasks_done']}/{roadmap.stats['total_tasks']} tasks "
            f"({roadmap.stats['completion_pct']}% complete)\n"
        )
    
        for org in roadmap.orgs:
            lines.append(f"## {org.name}")
            for proj in org.projects:
                # Filter by project if specified
                if project_filter and proj.id.lower() != project_filter:
                    continue
    
                lines.append(f"\n### {proj.name}")
                if proj.description:
                    lines.append(f"_{proj.description}_\n")
                lines.append(f"Tickets: {proj.tickets_done}/{proj.ticket_count} done\n")
    
                # Filter tickets
                tickets = proj.tickets
                if active_only:
                    tickets = [t for t in tickets if t.status.value != "done"]
    
                for ticket in tickets[:20]:  # Limit to 20 tickets per project
                    status_icon = {
                        "backlog": "[ ]",
                        "planned": "[P]",
                        "in-progress": "[~]",
                        "done": "[x]",
                        "blocked": "[!]",
                    }.get(ticket.status.value, "[ ]")
                    prio = (
                        f"({ticket.priority.value})"
                        if ticket.priority.value in ["critical", "high"]
                        else ""
                    )
                    lines.append(f"- {status_icon} **{ticket.id}**: {ticket.title} {prio}")
                    lines.append(f"  Tasks: {ticket.tasks_done}/{ticket.task_count}")
    
                    # Show incomplete tasks (max 3)
                    incomplete = [t for t in ticket.tasks if t.status.value != "done"]
                    for task in incomplete[:3]:
                        t_icon = {"pending": "[ ]", "in-progress": "[~]", "blocked": "[!]"}.get(
                            task.status.value, "[ ]"
                        )
                        lines.append(f"    - {t_icon} {task.id}: {task.title}")
                    if len(incomplete) > 3:
                        lines.append(f"    - ... and {len(incomplete) - 3} more")
    
                if len(tickets) > 20:
                    lines.append(f"\n_... and {len(tickets) - 20} more tickets_")
    
        return "\n".join(lines)
  • Tool registration in list_tools(), including name, description, and inputSchema.
            Tool(
                name="roadmap_view",
                description="""PROJECT MANAGEMENT (TPM): Get project roadmap showing work status.
    
    USE THIS TOOL WHEN:
    - User asks "what's in progress?" or "what are we working on?"
    - User asks "TPM status", ":TPM:" prefix, or "show me the roadmap"
    - User asks about pending/blocked/completed work
    - Starting a work session to see current state
    - User completes work and you need to find related tasks to mark done
    
    Returns summary of organizations, projects, and tickets. Use project_id filter to reduce output.""",
                inputSchema={
                    "type": "object",
                    "properties": {
                        "org_id": {
                            "type": "string",
                            "description": "Filter by organization ID (optional) case-insensitive",
                        },
                        "project_id": {
                            "type": "string",
                            "description": "Filter by project ID (optional) - recommended to reduce output size",
                        },
                        "active_only": {
                            "type": "boolean",
                            "description": "Only show non-done tickets (default: true)",
                            "default": True,
                        },
                    },
                },
            ),
  • Pydantic model RoadmapView used as return type for get_roadmap and processed in handler.
    class RoadmapView(BaseModel):
        """Full roadmap at a glance."""
    
        orgs: list[OrgView] = Field(default_factory=list)
        stats: dict = Field(default_factory=dict)
  • Database method get_roadmap that constructs the RoadmapView by aggregating orgs, projects, tickets, tasks and computes stats.
    def get_roadmap(self, org_id: str | None = None) -> RoadmapView:
        """Get full roadmap view with stats."""
        orgs = self.list_orgs()
        if org_id:
            org_id = self._normalize_id(org_id)
            orgs = [o for o in orgs if o.id.lower() == org_id]
    
        org_views = []
        total_tickets = 0
        tickets_done = 0
        total_tasks = 0
        tasks_done = 0
    
        for org in orgs:
            projects = self.list_projects(org.id)
            project_views = []
    
            for proj in projects:
                tickets = self.list_tickets(proj.id)
                ticket_views = []
                proj_tickets_done = 0
    
                for ticket in tickets:
                    tasks = self.list_tasks(ticket.id)
                    task_views = [
                        TaskView(
                            id=t.id,
                            title=t.title,
                            status=t.status,
                            priority=t.priority,
                            complexity=t.complexity,
                        )
                        for t in tasks
                    ]
                    ticket_tasks_done = sum(
                        1 for t in tasks if t.status in (TaskStatus.DONE, TaskStatus.COMPLETED)
                    )
    
                    ticket_views.append(
                        TicketView(
                            id=ticket.id,
                            title=ticket.title,
                            status=ticket.status,
                            priority=ticket.priority,
                            tags=ticket.tags,
                            task_count=len(tasks),
                            tasks_done=ticket_tasks_done,
                            tasks=task_views,
                        )
                    )
    
                    total_tasks += len(tasks)
                    tasks_done += ticket_tasks_done
                    if ticket.status in (TicketStatus.DONE, TicketStatus.COMPLETED):
                        proj_tickets_done += 1
    
                project_views.append(
                    ProjectView(
                        id=proj.id,
                        name=proj.name,
                        description=proj.description,
                        ticket_count=len(tickets),
                        tickets_done=proj_tickets_done,
                        tickets=ticket_views,
                    )
                )
                total_tickets += len(tickets)
                tickets_done += proj_tickets_done
    
            org_views.append(OrgView(id=org.id, name=org.name, projects=project_views))
    
        return RoadmapView(
            orgs=org_views,
            stats={
                "total_tickets": total_tickets,
                "tickets_done": tickets_done,
                "total_tasks": total_tasks,
                "tasks_done": tasks_done,
                "completion_pct": round(tasks_done / total_tasks * 100, 1)
                if total_tasks > 0
                else 0,
            },
        )
Behavior4/5

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. It effectively describes what the tool returns ('summary of organizations, projects, and tickets'), output characteristics ('reduce output size' warning), and filtering behavior. However, it doesn't mention potential rate limits, authentication needs, or error conditions, leaving some behavioral aspects uncovered.

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 well-structured with clear sections (purpose statement, usage guidelines, return information, parameter advice). Every sentence earns its place by providing specific guidance without redundancy. The information is front-loaded with the core purpose stated first, followed by practical usage scenarios.

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

Completeness4/5

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

Given the tool's moderate complexity (3 parameters, no output schema, no annotations), the description provides good contextual coverage. It explains the tool's purpose, when to use it, what it returns, and includes a practical tip about output size. The main gap is the lack of output format details, but this is partially compensated by the clear behavioral description of what the summary contains.

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 input schema has 100% description coverage, providing clear documentation for all 3 parameters. The description adds minimal parameter semantics beyond the schema, only mentioning 'Use project_id filter to reduce output' which slightly reinforces the schema's 'recommended to reduce output size' note. This meets the baseline expectation when schema coverage is high.

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

Purpose5/5

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

The description clearly states the tool's purpose: 'Get project roadmap showing work status' with specific verbs ('get', 'showing') and resources ('project roadmap', 'work status'). It distinguishes itself from sibling tools like task_list, ticket_list, or project_list by focusing on a comprehensive status overview rather than simple listings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit usage guidelines with a dedicated 'USE THIS TOOL WHEN:' section listing 5 specific scenarios (e.g., user asks about progress, TPM status, pending work, starting sessions, completing work). It clearly differentiates when to use this tool versus alternatives by emphasizing its role for status overviews rather than individual task/ticket operations.

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/urjitbhatia/tpm-mcp'

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