Skip to main content
Glama

task_create

Create a task in OmniFocus inbox, project, or as a subtask. Supports due dates, notes, tags, and flags.

Instructions

Create a new task in OmniFocus — in the inbox, inside a project, or as a subtask of another task. Supply exactly one of: projectId (project task), parentTaskId (subtask), or neither (inbox). Do not use for bulk creation; prefer task_batch_create for that. Safety control: pass idempotency_key to make transport retries safe — identical subsequent calls within the TTL window replay the original envelope with meta.idempotentReplay = true instead of creating a duplicate task. Returns { id, name } — name echoes the supplied name so the agent can describe the new task without a follow-up read. Side effects: creates a task in OmniFocus, sets meta.syncPending = true. Call sync_trigger when you need the task to appear on other devices. Example: task_create({ name: "Buy milk" }) Example: task_create({ name: "Write report", projectId: "prj123", dueDate: "2026-05-01T00:00:00Z" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesTask name. Required, must be non-empty.
noteNoPlain-text note.
tagIdsNoTag IDs to apply.
dueDateNoDue date as ISO-8601 with offset.
flaggedNoFlag the task.
deferDateNoDefer date as ISO-8601 with offset.
projectIdNoProject to add the task to. Omit for inbox or subtask.
sequentialNoIf true, subtasks must be completed in order.
parentTaskIdNoParent task ID for a subtask. Omit for inbox or project task.
dueDateFloatingNoWhen true, the due time follows the user across time zones (floating) rather than being pinned to a fixed UTC instant. Use for recurring daily tasks where '9 AM' should mean 9 AM wherever the user is. Default: false (fixed-offset).
idempotency_keyNoIdempotency key for retry-safe creates. Identical subsequent calls within the TTL window replay the original envelope with meta.idempotentReplay = true instead of creating a duplicate task.
estimatedMinutesNoEstimated duration in minutes.
deferDateFloatingNoWhen true, the defer time is floating (follows the user across time zones).
completedByChildrenNoComplete when all subtasks complete.
Behavior5/5

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

Given no annotations, the description fully discloses behavioral traits: side effects (creates task, sets meta.syncPending = true), idempotency replay behavior, return value format ({ id, name } with name echo), and when sync_trigger is needed. This exceeds typical transparency.

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

Conciseness4/5

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

The description is well-structured: purpose first, then placement rules, bulk warning, safety, return value, side effects, and examples. It is slightly long but efficient, with every sentence adding value. Front-loading is good.

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?

With 14 parameters and no output schema, the description covers all critical aspects: placement options, idempotency, return format, side effects, and syncing. It leaves no major gaps for this mutation tool.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description adds meaningful context: clarifies mutual exclusivity of projectId/parentTaskId, explains dueDateFloating behavior (time zone following), and details idempotency_key effect. This goes beyond schema descriptions.

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 verb and resource ('Create a new task') and distinguishes the three placement options (inbox, project, subtask). It also explicitly calls out the sibling tool task_batch_create for bulk creation, establishing clear differentiation.

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

Usage Guidelines5/5

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

Provides explicit when-to-use guidance: 'Supply exactly one of: projectId, parentTaskId, or neither (inbox).' It also advises against bulk creation and points to task_batch_create. Additionally, it explains idempotency key usage for safe retries and mentions side effects with sync_trigger.

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/torsday/omnifocus-mcp'

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