Skip to main content
Glama
claus-92

Super Productivity MCP Server

by claus-92

search_tasks

Search for tasks by title with optional filters for project, tag, completion status, and source to quickly find specific tasks.

Instructions

Searches tasks by title text and optional filters.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesText to search for in the task title
projectIdNoFilter by project ID
projectNameNoFilter by project name
tagIdNoFilter by tag ID
tagNameNoFilter by tag name
includeDoneNoInclude completed tasks
sourceNoWhich task source to query

Implementation Reference

  • The handler function that executes the search_tasks tool logic: resolves filter IDs (project/tag) and calls SpClient.getTasks with the query and optional filters, returning the results.
    server.tool(
      "search_tasks",
      "Searches tasks by title text and optional filters.",
      {
        query: nonEmptyString.describe("Text to search for in the task title"),
        projectId: nonEmptyString.optional().describe("Filter by project ID"),
        projectName: nonEmptyString.optional().describe("Filter by project name"),
        tagId: nonEmptyString.optional().describe("Filter by tag ID"),
        tagName: nonEmptyString.optional().describe("Filter by tag name"),
        includeDone: z.boolean().optional().describe("Include completed tasks"),
        source: z.enum(["active", "archived", "all"]).optional().describe("Which task source to query"),
      },
      async ({ query, projectId, projectName, tagId, tagName, includeDone, source }) => {
        const resolved = await resolveTaskFilterIds({ projectId, projectName, tagId, tagName });
        const tasks = await SpClient.getTasks({
          query,
          projectId: resolved.projectId,
          tagId: resolved.tagId,
          includeDone,
          source,
        });
        return ok(tasks);
      }
  • Input schema for search_tasks defining parameters: query (required non-empty string), projectId, projectName, tagId, tagName (optional strings), includeDone (optional boolean), source (optional enum: active/archived/all).
    server.tool(
      "search_tasks",
      "Searches tasks by title text and optional filters.",
      {
        query: nonEmptyString.describe("Text to search for in the task title"),
        projectId: nonEmptyString.optional().describe("Filter by project ID"),
        projectName: nonEmptyString.optional().describe("Filter by project name"),
        tagId: nonEmptyString.optional().describe("Filter by tag ID"),
        tagName: nonEmptyString.optional().describe("Filter by tag name"),
        includeDone: z.boolean().optional().describe("Include completed tasks"),
        source: z.enum(["active", "archived", "all"]).optional().describe("Which task source to query"),
      },
  • Registration of the search_tasks tool via server.tool() on the McpServer instance.
    server.tool(
      "search_tasks",
      "Searches tasks by title text and optional filters.",
      {
        query: nonEmptyString.describe("Text to search for in the task title"),
        projectId: nonEmptyString.optional().describe("Filter by project ID"),
        projectName: nonEmptyString.optional().describe("Filter by project name"),
        tagId: nonEmptyString.optional().describe("Filter by tag ID"),
        tagName: nonEmptyString.optional().describe("Filter by tag name"),
        includeDone: z.boolean().optional().describe("Include completed tasks"),
        source: z.enum(["active", "archived", "all"]).optional().describe("Which task source to query"),
      },
      async ({ query, projectId, projectName, tagId, tagName, includeDone, source }) => {
        const resolved = await resolveTaskFilterIds({ projectId, projectName, tagId, tagName });
        const tasks = await SpClient.getTasks({
          query,
          projectId: resolved.projectId,
          tagId: resolved.tagId,
          includeDone,
          source,
        });
        return ok(tasks);
      }
  • Helper constant nonEmptyString used in the schema (z.string().trim().min(1)).
    const nonEmptyString = z.string().trim().min(1);
  • Helper function resolveTaskFilterIds used by search_tasks to resolve optional projectName/tagName to IDs.
    async function resolveTaskFilterIds(params: {
      projectId?: string;
      projectName?: string;
      tagId?: string;
      tagName?: string;
    }) {
      if (!params.projectName && !params.tagName) {
        return {
          projectId: params.projectId,
          tagId: params.tagId,
        };
      }
    
      const [projects, tags] = await Promise.all([
        params.projectName ? SpClient.getProjects() : Promise.resolve([]),
        params.tagName ? SpClient.getTags() : Promise.resolve([]),
      ]);
    
      return {
        projectId: resolveProjectId(projects, params.projectId, params.projectName),
        tagId: resolveTagId(tags, params.tagId, params.tagName),
      };
    }
Behavior2/5

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

With no annotations provided, the description bears full burden for behavioral disclosure. It only says 'searches', which suggests a read operation, but does not mention that it is read-only, any authentication requirements, rate limits, pagination behavior, or potential side effects. The behavioral trait is minimal.

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 a single, front-loaded sentence with no extraneous words. It efficiently conveys the tool's core function without redundancy.

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?

The tool has no output schema, so the description should explain what the search returns (e.g., list of task objects, count, etc.). It does not mention return format, result limits, or ordering. The description is incomplete for a search tool that produces results.

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, meaning all parameters are already documented. The description adds 'optional filters' which is generic and does not provide additional meaning beyond what the schema already conveys. Baseline score of 3 is appropriate.

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 action (searches), the resource (tasks), and the specific search criterion (by title text). This differentiates it from sibling tools like list_tasks (likely lists all tasks without filter) and get_task (retrieves by ID). The verb 'searches' is specific and unambiguous.

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

Usage Guidelines3/5

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

The description implies the tool is for searching tasks by title and applying optional filters, but does not explicitly state when to use it versus alternatives like list_tasks or get_task. No guidance is given on when not to use it or typical use cases.

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/claus-92/super-productivity-mcp'

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