Skip to main content
Glama
HuntsDesk

Vibe Board VE

by HuntsDesk
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

board_delete_task

Delete a task and optionally its subtasks. Default safety restricts deletion to completed tasks to prevent accidental removal. Irreversible action.

Instructions

Hard-delete a task and optionally its subtasks. Safety guard: by default only allows deleting tasks with status=done (prevents deleting in-progress work). Pass require_done=false to override. Also deletes associated activity_log entries. This is irreversible — cannot be undone.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
task_idYesTask ID to delete
require_doneNoIf true (default), refuse to delete unless the task's status is 'done'. Pass false to force-delete a non-done task.
cascade_subtasksNoIf true, also delete all tasks with parent_task_id == task_id (each child also subject to require_done check). Default false — subtasks are orphaned but kept.

Implementation Reference

  • src/tools/tasks.ts:701-818 (handler)
    The handler function for board_delete_task. Receives task_id, require_done, and cascade_subtasks params. Fetches the task doc from Firestore, checks if it exists, validates require_done guard, optionally cascades to subtasks, deletes associated activity_log entries, deletes the task docs, and writes an audit entry.
      async ({ task_id, require_done, cascade_subtasks }) => {
    const requireDone = require_done ?? true;
    const cascade = cascade_subtasks ?? false;

    const taskRef = db.collection("tasks").doc(task_id);
    const taskSnap = await taskRef.get();
    if (!taskSnap.exists) {
      return {
        content: [
          {
            type: "text" as const,
            text: JSON.stringify({ error: `Task ${task_id} not found` }),
          },
        ],
      };
    }

    const data = taskSnap.data() ?? {};
    if (requireDone && data.status !== "done") {
      return {
        content: [
          {
            type: "text" as const,
            text: JSON.stringify({
              error: `Task ${task_id} has status="${data.status}". Set status to "done" first, or pass require_done=false to force delete. Refusing to delete in-progress work.`,
            }),
          },
        ],
      };
    }

    const toDelete: string[] = [task_id];
    if (cascade) {
      const childrenSnap = await db
        .collection("tasks")
        .where("parent_task_id", "==", task_id)
        .get();
      for (const child of childrenSnap.docs) {
        const childData = child.data() ?? {};
        if (requireDone && childData.status !== "done") {
          return {
            content: [
              {
                type: "text" as const,
                text: JSON.stringify({
                  error: `Subtask ${child.id} has status="${childData.status}". Parent ${task_id} not deleted. Either complete subtasks first or pass require_done=false.`,
                }),
              },
            ],
          };
        }
        toDelete.push(child.id);
      }
    }

    // Gather activity_log entries for the tasks being deleted.
    const activityRefs: FirebaseFirestore.DocumentReference[] = [];
    for (const id of toDelete) {
      const activitySnap = await db
        .collection("activity_log")
        .where("task_id", "==", id)
        .get();
      for (const doc of activitySnap.docs) activityRefs.push(doc.ref);
    }

    // Delete in order: activity_log entries first, task docs last. If the
    // multi-batch loop fails mid-way, we'd rather have a task doc with
    // truncated history than an orphaned history pointing at a deleted
    // task_id. Task deletions go in the final batch so they're atomic
    // with the most recent history writes. Firestore batch limit is 500
    // writes; chunk at 450 to leave headroom.
    const CHUNK = 450;
    // Activity log first (in chunks).
    for (let i = 0; i < activityRefs.length; i += CHUNK) {
      const batch = db.batch();
      for (const ref of activityRefs.slice(i, i + CHUNK)) batch.delete(ref);
      await batch.commit();
    }
    // Task docs last, all together (≤100 cascade limit, well under 500).
    const taskBatch = db.batch();
    for (const id of toDelete) taskBatch.delete(db.collection("tasks").doc(id));
    await taskBatch.commit();

    // Write a final audit entry for the deletion itself. Because the task
    // is gone, this entry has task_id=null and details capture what was removed.
    await db.collection("activity_log").add({
      task_id: null,
      session_id: null,
      agent_name: "system",
      action: "updated",
      details: `Deleted task${cascade && toDelete.length > 1 ? `s` : ""}: ${toDelete.join(", ")}`,
      metadata: {
        deleted_task_ids: toDelete,
        deleted_activity_count: activityRefs.length,
        require_done: requireDone,
        cascade_subtasks: cascade,
      },
      created_at: Timestamp.now(),
    });

    return {
      content: [
        {
          type: "text" as const,
          text: JSON.stringify(
            {
              deleted_task_ids: toDelete,
              deleted_activity_entries: activityRefs.length,
              message: `Deleted ${toDelete.length} task(s) and ${activityRefs.length} activity log entries.`,
            },
            null,
            2
          ),
        },
      ],
    };
  }
);
  • src/tools/tasks.ts:686-700 (schema)
    Input schema for board_delete_task defining three parameters: task_id (string, required), require_done (boolean, optional, defaults to true), and cascade_subtasks (boolean, optional, defaults to false).
    {
  task_id: z.string().describe("Task ID to delete"),
  require_done: z
    .boolean()
    .optional()
    .describe(
      "If true (default), refuse to delete unless the task's status is 'done'. Pass false to force-delete a non-done task."
    ),
  cascade_subtasks: z
    .boolean()
    .optional()
    .describe(
      "If true, also delete all tasks with parent_task_id == task_id (each child also subject to require_done check). Default false — subtasks are orphaned but kept."
    ),
},
  • src/tools/tasks.ts:683-818 (registration)
    Registration of 'board_delete_task' tool via server.tool() with description, schema, and handler. Part of the registerTaskTools function.
    server.tool(
  "board_delete_task",
  "Hard-delete a task and optionally its subtasks. Safety guard: by default only allows deleting tasks with status=done (prevents deleting in-progress work). Pass require_done=false to override. Also deletes associated activity_log entries. This is irreversible — cannot be undone.",
  {
    task_id: z.string().describe("Task ID to delete"),
    require_done: z
      .boolean()
      .optional()
      .describe(
        "If true (default), refuse to delete unless the task's status is 'done'. Pass false to force-delete a non-done task."
      ),
    cascade_subtasks: z
      .boolean()
      .optional()
      .describe(
        "If true, also delete all tasks with parent_task_id == task_id (each child also subject to require_done check). Default false — subtasks are orphaned but kept."
      ),
  },
  async ({ task_id, require_done, cascade_subtasks }) => {
    const requireDone = require_done ?? true;
    const cascade = cascade_subtasks ?? false;

    const taskRef = db.collection("tasks").doc(task_id);
    const taskSnap = await taskRef.get();
    if (!taskSnap.exists) {
      return {
        content: [
          {
            type: "text" as const,
            text: JSON.stringify({ error: `Task ${task_id} not found` }),
          },
        ],
      };
    }

    const data = taskSnap.data() ?? {};
    if (requireDone && data.status !== "done") {
      return {
        content: [
          {
            type: "text" as const,
            text: JSON.stringify({
              error: `Task ${task_id} has status="${data.status}". Set status to "done" first, or pass require_done=false to force delete. Refusing to delete in-progress work.`,
            }),
          },
        ],
      };
    }

    const toDelete: string[] = [task_id];
    if (cascade) {
      const childrenSnap = await db
        .collection("tasks")
        .where("parent_task_id", "==", task_id)
        .get();
      for (const child of childrenSnap.docs) {
        const childData = child.data() ?? {};
        if (requireDone && childData.status !== "done") {
          return {
            content: [
              {
                type: "text" as const,
                text: JSON.stringify({
                  error: `Subtask ${child.id} has status="${childData.status}". Parent ${task_id} not deleted. Either complete subtasks first or pass require_done=false.`,
                }),
              },
            ],
          };
        }
        toDelete.push(child.id);
      }
    }

    // Gather activity_log entries for the tasks being deleted.
    const activityRefs: FirebaseFirestore.DocumentReference[] = [];
    for (const id of toDelete) {
      const activitySnap = await db
        .collection("activity_log")
        .where("task_id", "==", id)
        .get();
      for (const doc of activitySnap.docs) activityRefs.push(doc.ref);
    }

    // Delete in order: activity_log entries first, task docs last. If the
    // multi-batch loop fails mid-way, we'd rather have a task doc with
    // truncated history than an orphaned history pointing at a deleted
    // task_id. Task deletions go in the final batch so they're atomic
    // with the most recent history writes. Firestore batch limit is 500
    // writes; chunk at 450 to leave headroom.
    const CHUNK = 450;
    // Activity log first (in chunks).
    for (let i = 0; i < activityRefs.length; i += CHUNK) {
      const batch = db.batch();
      for (const ref of activityRefs.slice(i, i + CHUNK)) batch.delete(ref);
      await batch.commit();
    }
    // Task docs last, all together (≤100 cascade limit, well under 500).
    const taskBatch = db.batch();
    for (const id of toDelete) taskBatch.delete(db.collection("tasks").doc(id));
    await taskBatch.commit();

    // Write a final audit entry for the deletion itself. Because the task
    // is gone, this entry has task_id=null and details capture what was removed.
    await db.collection("activity_log").add({
      task_id: null,
      session_id: null,
      agent_name: "system",
      action: "updated",
      details: `Deleted task${cascade && toDelete.length > 1 ? `s` : ""}: ${toDelete.join(", ")}`,
      metadata: {
        deleted_task_ids: toDelete,
        deleted_activity_count: activityRefs.length,
        require_done: requireDone,
        cascade_subtasks: cascade,
      },
      created_at: Timestamp.now(),
    });

    return {
      content: [
        {
          type: "text" as const,
          text: JSON.stringify(
            {
              deleted_task_ids: toDelete,
              deleted_activity_entries: activityRefs.length,
              message: `Deleted ${toDelete.length} task(s) and ${activityRefs.length} activity log entries.`,
            },
            null,
            2
          ),
        },
      ],
    };
  }
);
  • src/tools/tasks.ts:5-5 (helper)
    The registerTaskTools function that wraps all task tool registrations, including board_delete_task. Called from src/index.ts:29.
    export function registerTaskTools(server: McpServer, db: Firestore) {
  • src/index.ts:29-29 (registration)
    Where registerTaskTools is invoked, registering all task tools including board_delete_task on the MCP server.
    registerTaskTools(server, db);

Tool Definition Quality

A4.5/5.0
Behavior5/5

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

No annotations provided, so the description fully shoulders behavioral disclosure. It reveals irreversibility, hard-delete nature, cascading subtasks, deletion of activity_log entries, and the require_done safety guard. This is comprehensive.

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?

Three sentences conveying all essential information without fluff. Front-loaded with the core action, then safety and side effects. Highly efficient.

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

Completeness5/5

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

Despite no output schema, the description covers required parameters, side effects (activity_log), irreversibility, and safety guard. Sufficient for an agent to use the tool correctly.

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?

Input schema has 100% coverage with descriptions for all 3 parameters. The description adds some extra nuance (e.g., 'Pass require_done=false to override'), but does not significantly exceed the schema. Baseline 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?

Clearly states it hard-deletes a task and optionally its subtasks. The verb 'delete' and resource 'task' are specific, and it distinguishes from siblings like board_update_task or board_create_task which are not delete operations.

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

Usage Guidelines4/5

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

Provides context on when to use (deleting done tasks) and safety guard to prevent deleting in-progress work. However, it does not explicitly compare with sibling tools or suggest alternatives for other 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/HuntsDesk/ve-vibe-board'

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