Skip to main content
Glama

summarize-project

Generate concise summaries of Things 3 projects by analyzing task structure and content to provide quick overviews of project scope and status.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_uuidYesUUID of the project to summarize

Implementation Reference

  • Registration of the 'summarize-project' tool in src/index.ts.
      "summarize-project",
      {
        project_uuid: z.string().describe("UUID of the project to summarize"),
      },
      async ({ project_uuid }) => {
        const summary = await withDatabase((db) =>
          summarizeProject(getAllTasks(db), project_uuid)
        );
    
        return buildTextResponse(`Summarized project ${summary.project.title}`, summary);
      }
    );
  • The core implementation of the project summarization logic in src/project-summary.ts.
    export function summarizeProject(tasks: TaskLike[], projectUuid: string) {
      const today = todayDateOnly();
      const structure = buildProjectStructure(tasks, projectUuid);
      const headingDistribution = headingStatsFor(structure);
    
      const sortedByLoad = [...headingDistribution].sort(
        (a, b) => b.todoCount - a.todoCount || a.headingTitle.localeCompare(b.headingTitle)
      );
      const busiestHeading = sortedByLoad.find((entry) => entry.todoCount > 0) ?? null;
      const emptiestHeadings = headingDistribution.filter((entry) => entry.todoCount === 0);
    
      const completedTodos = structure.todos.filter((todo) => todo.status === "completed").length;
      const canceledTodos = structure.todos.filter((todo) => todo.status === "canceled").length;
      const incompleteTodos = structure.todos.filter((todo) => todo.status === "incomplete").length;
      const overdue = overdueTasks(structure.todos, today);
      const upcoming = upcomingTasks(structure.todos, today);
      const planningPriority = inferPlanningPriority({
        overdueCount: overdue.length,
        withoutHeadingCount: structure.todosWithoutHeading.length,
        emptyHeadingCount: emptiestHeadings.length,
        incompleteCount: incompleteTodos,
      });
    
      const observations: string[] = [];
      if (busiestHeading) {
        observations.push(
          `El heading con más carga actual es ${busiestHeading.headingTitle} (${busiestHeading.todoCount} tareas, ${busiestHeading.incomplete} incompletas).`
        );
      }
      if (emptiestHeadings.length > 0) {
        observations.push(
          `Hay ${emptiestHeadings.length} headings sin tareas: ${emptiestHeadings.map((entry) => entry.headingTitle).join(", ")}.`
        );
      }
      if (structure.todosWithoutHeading.length > 0) {
        observations.push(`Hay ${structure.todosWithoutHeading.length} tareas sin heading asignado.`);
      }
      if (overdue.length > 0) {
        observations.push(`Hay ${overdue.length} tareas vencidas que requieren atención.`);
      }
      if (upcoming.length > 0) {
        observations.push(`Hay ${upcoming.length} tareas con fecha próxima o activa para revisar.`);
      }
      if (observations.length === 0) {
        observations.push("La estructura del proyecto se ve balanceada y sin huecos obvios.");
      }
    
      const nextActions: string[] = [];
      if (overdue.length > 0) {
        nextActions.push("Atender o reprogramar primero las tareas vencidas.");
      }
      if (structure.todosWithoutHeading.length > 0) {
        nextActions.push("Ubicar las tareas sin heading para mantener la estructura consistente.");
      }
      if (emptiestHeadings.length > 0) {
        nextActions.push("Revisar si los headings vacíos siguen siendo útiles o si conviene poblarlos con próximas tareas.");
      }
      if (upcoming.length > 0) {
        nextActions.push("Confirmar las próximas tareas activas para que reflejen la prioridad real del proyecto.");
      }
      if (!nextActions.length) {
        nextActions.push("Usar la estructura actual del proyecto como base para seguir agregando tareas nuevas.");
      }
    
      const planningSignals = {
        planningPriority,
        hasOverdueWork: overdue.length > 0,
        hasUnassignedTasks: structure.todosWithoutHeading.length > 0,
        hasEmptyHeadings: emptiestHeadings.length > 0,
        isStructureBalanced:
          overdue.length === 0 &&
          structure.todosWithoutHeading.length === 0 &&
          emptiestHeadings.length === 0,
      };
    
      return {
        project: structure.compact.project,
        counts: {
          headings: structure.headings.length,
          todos: structure.todos.length,
          incompleteTodos,
          completedTodos,
          canceledTodos,
          todosWithoutHeading: structure.todosWithoutHeading.length,
          overdueTodos: overdue.length,
          upcomingTodos: upcoming.length,
        },
        headingDistribution,
        busiestHeading,
        emptyHeadings: emptiestHeadings,
        overdue,
        upcoming,
        planningSignals,
        observations,
        nextActions,
        summaryText: [
          `Proyecto: ${structure.project.title}.`,
          `Tiene ${structure.headings.length} headings y ${structure.todos.length} tareas.`,
          structure.todosWithoutHeading.length > 0
            ? `${structure.todosWithoutHeading.length} tareas siguen sin heading.`
            : "No hay tareas sin heading.",
          overdue.length > 0
            ? `Hay ${overdue.length} tareas vencidas.`
            : "No hay tareas vencidas.",
          busiestHeading
            ? `La mayor concentración de tareas está en ${busiestHeading.headingTitle}.`
            : "Todavía no hay un heading dominante.",
          `Prioridad de planificación: ${planningPriority}.`,
        ].join(" "),
      };
    }
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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/soycanopa/SupaThings-MCP'

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