Skip to main content
Glama

search-advanced

Search and filter tasks in Things 3 using criteria like status, dates, tags, and areas to find specific items for management.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusNoincomplete, completed, or canceled
start_dateNoStart date in YYYY-MM-DD
deadlineNoDeadline in YYYY-MM-DD
tagNoTag title
areaNoArea UUID or title
typeNoto-do, project, or heading
lastNoCreated within period like 3d or 1w
detailNoResponse detail level. Defaults to compact.
limitNoMaximum number of items to return

Implementation Reference

  • The handler for the "search-advanced" MCP tool, which filters and returns tasks based on various optional parameters.
    server.tool(
      "search-advanced",
      {
        status: z.string().optional().describe("incomplete, completed, or canceled"),
        start_date: z.string().optional().describe("Start date in YYYY-MM-DD"),
        deadline: z.string().optional().describe("Deadline in YYYY-MM-DD"),
        tag: z.string().optional().describe("Tag title"),
        area: z.string().optional().describe("Area UUID or title"),
        type: z.string().optional().describe("to-do, project, or heading"),
        last: z.string().optional().describe("Created within period like 3d or 1w"),
        detail: z.enum(["compact", "full"]).optional().describe("Response detail level. Defaults to compact."),
        limit: z.number().int().positive().optional().describe("Maximum number of items to return"),
      },
      async (params) => {
        const requestedDetail = params.detail ?? "compact";
        const results = await withDatabase((db) => {
          let tasks = getAllTasks(db).filter((task) => !task.trashed);
    
          if (params.status) {
            tasks = tasks.filter((task) => task.status === params.status?.toLowerCase());
          }
    
          if (params.start_date) {
            tasks = tasks.filter((task) => task.startDate === params.start_date);
          }
    
          if (params.deadline) {
            tasks = tasks.filter((task) => task.deadline === params.deadline);
          }
    
          if (params.tag) {
            tasks = tasks.filter((task) => task.tags.includes(params.tag!));
          }
    
          if (params.area) {
            const lower = params.area.toLowerCase();
            tasks = tasks.filter(
              (task) =>
                task.areaId?.toLowerCase() === lower ||
                task.areaTitle?.toLowerCase() === lower
            );
          }
    
          if (params.type) {
            tasks = tasks.filter((task) => task.type === params.type);
          }
    
          if (params.last) {
            const since = parseRelativePeriod(params.last);
            tasks = tasks.filter(
              (task) => task.created && new Date(task.created) >= since
            );
          }
    
          return applyLimit(tasks, params.limit).map((task) =>
            toTaskView(task, requestedDetail)
          );
        });
    
        return buildTextResponse(`Found ${results.length} matching items`, {
          results,
          detail: requestedDetail,
          limit: params.limit ?? null,
        });
      }
    );
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