Skip to main content
Glama

task_update_describe

Preview task edits before committing changes. Inspect planned modifications to verify accuracy, then apply the update. Read-only dry-run, no side effects.

Instructions

Preview what task_update would do without making any changes. Do NOT use to actually update a task — use task_update instead. Returns { description, plannedChanges } showing the fields that would be patched. No side effects: read-only by contract — never mutates OmniFocus. Example: dry-run companion — pass the same args you would to the write tool, inspect plannedChanges, then call the write tool once approved.

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.
Behavior4/5

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

With no annotations, the description carries full burden. It states 'No side effects: read-only by contract — never mutates OmniFocus,' which is a key behavioral trait. It also mentions the return envelope format. However, it does not detail error conditions (e.g., invalid id) or behavior when dry_run parameter is not set (the parameter exists in schema but not mentioned in description). Still, the main behavioral aspect is well-covered.

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 a single paragraph with four sentences covering purpose, warning, output, and usage. It is clear and efficient, but could be slightly more structured (e.g., bullet points for key points). No unnecessary words, but not maximally concise.

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?

Given the tool is a dry-run preview with no output schema, the description explains the return value (plannedChanges) and the read-only nature. It also gives a usage example. However, it omits mention of the dry_run parameter (exists in schema) and does not cover what happens if the update would fail validation, which would be useful for a preview tool.

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 baseline is 3. The description does not add per-parameter detail beyond the schema; it does add overall context (same args as task_update, returns plannedChanges). But since schema already has thorough descriptions, the description does not significantly improve parameter understanding.

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 it previews task_update without making changes, explicitly distinguishes from task_update, and specifies the output (description, plannedChanges). The verb 'preview' and resource are unambiguous.

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?

The description explicitly tells when to use (before task_update), when not to use (not for actual updates), and provides a usage pattern: pass same args, inspect plannedChanges, then call write tool. It names the alternative (task_update) and explains the companion relationship.

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