Google Workspace MCP Server - Control Gmail, Calendar, Docs, Sheets, Slides, Chat, Forms & Drive

Manage Task

manage_task

Destructive

Create, update, delete, or move tasks in Google Tasks lists directly from your AI assistant.

Instructions

Manage tasks: create, update, delete, or move tasks within task lists.

Input Schema

TableJSON Schema

Name	Required	Description
`due`	No	Due date in RFC 3339 format (e.g., "2024-12-31T23:59:59Z"). Used by "create" and "update" actions.
`notes`	No	Notes/description for the task. Used by "create" and "update" actions.
`title`	No	The title of the task. Required for "create", optional for "update".
`action`	Yes	The action to perform. Must be one of: "create", "update", "delete", "move".
`parent`	No	Parent task ID (for subtasks). Used by "create" and "move" actions.
`status`	No	Task status ("needsAction" or "completed"). Used by "update" action.
`task_id`	No	The ID of the task. Required for "update", "delete", and "move" actions.
`previous`	No	Previous sibling task ID (for positioning). Used by "create" and "move" actions.
`task_list_id`	Yes	The ID of the task list. Required for all actions.
`user_google_email`	Yes	The user's Google email address. Required.
`destination_task_list`	No	Destination task list ID (for moving between lists). Used by "move" action.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed16 schema fields changedv1.28.0Sep 24, 2026

removedInput schema / properties / destination_task_list / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / destination_task_list / type
```
Added value: +"string"
```

removedInput schema / properties / due / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / due / type
```
Added value: +"string"
```

removedInput schema / properties / notes / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / notes / type
```
Added value: +"string"
```

removedInput schema / properties / parent / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / parent / type
```
Added value: +"string"
```

removedInput schema / properties / previous / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / previous / type
```
Added value: +"string"
```

removedInput schema / properties / status / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / status / type
```
Added value: +"string"
```

removedInput schema / properties / task_id / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / task_id / type
```
Added value: +"string"
```

removedInput schema / properties / title / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedInput schema / properties / title / type
```
Added value: +"string"
```

Addedv1.0.1Jul 31, 2026

TDQS

A4/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the bar for extra disclosure is lower. The description adds the operation set, but most of that detail is also in the schema's action parameter. It does not disclose additional consequences (e.g., whether delete is permanent, how move affects position), though annotations mitigate the safety gap.

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 one efficient sentence, front-loading the resource and all key operations. It wastes no words and is easy to scan, making it highly usable for an agent quickly assessing the tool.

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?

The tool is complex (11 parameters, 4 action modes), but the schema is exhaustive and an output schema exists. The description provides the high-level operation overview while the schema and annotations supply detailed constraints, so nothing critical is missing for invoking 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?

Schema description coverage is 100%, so the baseline is 3. The description does not add meaning beyond the schema; each parameter is already thoroughly documented with per-action usage notes (e.g., 'Used by "create" and "update"'). No additional semantic value is contributed by the description.

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 states the resource ('tasks') and enumerates four concrete actions ('create, update, delete, or move tasks within task lists'), which clearly distinguishes it from siblings like 'list_tasks' or 'get_task'. It goes beyond a generic verb by naming the specific operations, making the tool's scope immediately obvious.

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?

The description clearly conveys the tool is for mutating tasks (create/update/delete/move), implying it should be used over read-only alternatives such as 'list_tasks' and 'get_task'. It does not explicitly name those alternatives or say when not to use this tool, so it falls short of a 5, but the action list provides clear usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server