Skip to main content
Glama

task_update

Update mutable fields of an OmniFocus task, including name, dates, flags, and tags, using full replacement or diff-based tag changes. Supports dry-run preview and optimistic concurrency.

Instructions

Partially update mutable fields on an OmniFocus task. Only supplied fields are changed; omit a field to leave it unchanged. Do not use to complete or delete a task; prefer task_complete or task_delete instead. Two tag-update modes: (1) supply tagIds to replace the full tag set; (2) supply addTags and/or removeTags to apply a diff without reading first. Supplying tagIds together with addTags/removeTags is a ValidationError. setFlagged is a convenience alias for flagged. Safety controls: set dry_run=true to preview the patched task without mutating; pass expectedModifiedAt (from a recent task_get) to reject the call if the task changed since you read it; pass idempotency_key to coalesce retries so the same update is only performed once. Returns the updated task. Side effects: writes to OmniFocus, sets meta.syncPending = true. Call sync_trigger when you need changes to appear on other devices. Example: task_update({ id: "abc123", flagged: true }) Example: task_update({ id: "abc123", dueDate: "2026-05-01T00:00:00Z", addTags: ["tag456"] })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesPersistent task ID. Get from task_list or search_query.
nameNoNew task name. Must be non-empty if supplied.
noteNoPlain-text note. Pass null to clear. HTML round-trip available in M3.
tagIdsNoFull-replacement tag list. Replaces all existing tags. Mutually exclusive with addTags/removeTags.
addTagsNoTags to add. No-op for tags the task already has. Mutually exclusive with tagIds.
dry_runNoWhen true, validates input, computes the patched task (pre-fetch merged with the supplied fields), and returns a preview envelope with meta.dryRun = true; no adapter call is made and no mutation occurs.
dueDateNoISO-8601 due date with UTC offset. Pass null to clear.
flaggedNoFlag or unflag the task. Alias: setFlagged.
deferDateNoISO-8601 defer date with UTC offset. Pass null to clear.
removeTagsNoTags to remove. No-op for tags the task doesn't have. Mutually exclusive with tagIds.
sequentialNoWhether subtasks must be completed in order.
setFlaggedNoConvenience alias for flagged. Use when your intent is specifically to set or clear the flag without touching other fields.
dueDateFloatingNoWhen true, the due time is floating (follows the user across time zones).
idempotency_keyNoIdempotency key for retry-safe updates. Identical subsequent calls within the TTL window replay the original envelope with meta.idempotentReplay = true instead of re-applying the patch.
estimatedMinutesNoEstimated duration in minutes. Pass null to clear.
deferDateFloatingNoWhen true, the defer time is floating (follows the user across time zones).
expectedModifiedAtNoOptimistic-concurrency guard: ISO-8601 timestamp from a recent task_get. If the task's current modifiedAt differs, the call fails with OF_CONFLICT and no update is performed. Omit to skip the check.
completedByChildrenNoWhether the task completes when all children are complete.
Behavior5/5

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

No annotations exist, so description bears full burden. Discloses partial update behavior, side effects (writes to OmniFocus, meta.syncPending), safety controls, tag mode mutual exclusivity, and concurrency guard. Thoroughly transparent.

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?

Well-structured: purpose first, then exclusions, tag modes, safety controls, examples. Every sentence is meaningful. No fluff despite length. Front-loaded with essential info.

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?

Given 18 params, no output schema, description covers purpose, exclusions, tag behavior, safety controls, side effects, concurrency, and example usage. Adequately complete for a complex 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 covers 100% of parameters, so baseline 3. Description adds context by explaining tag update modes, safety controls, and alias (setFlagged). Provides examples. Adds value 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?

Clearly states 'Partially update mutable fields on an OmniFocus task' and distinguishes from siblings by explicitly advising against using this for complete/delete, pointing to task_complete/task_delete. Also explains two tag-update modes.

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 and when-not-to-use guidance, naming alternatives. Explains tag modes, safety controls (dry_run, expectedModifiedAt, idempotency_key), and side effect of sync_trigger. Comprehensive context for selection.

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