Skip to main content
Glama

task_list

List tasks from OmniFocus with filters for project, tag, inbox, flagged, completion, and due dates to retrieve specific task sets.

Instructions

List tasks in OmniFocus with optional filters (project, tag, inbox, flagged, completion, due dates). Use inbox=true to fetch unprocessed Inbox tasks. Use this for filter-based queries across tasks. Do NOT use for a known single task (use task_get). For name-based lookup, prefer task_find_by_name. For full-text content search across names and notes, prefer search_query. Returns tasks[] with pagination; safe to call repeatedly; no side effects. Example: task_list({ inbox: true }) Example: task_list({ projectId: "prj123", flagged: true }) Example: task_list({ dueBefore: "2026-05-01T00:00:00Z", completed: "exclude" })

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inboxNotrue = Inbox tasks only (no project assignment). Cannot be combined with projectId or parentId. Use this to surface unprocessed captures without knowing their IDs.
limitNoMax tasks per page (1..1000). Default 50. Use `cursor` to fetch subsequent pages.
cursorNoOpaque cursor from a previous task_list response. Must use the same filters — changing filters mid-sequence returns a ValidationError.
fieldsNoRestrict each returned task to this list of top-level fields (id is always returned). Omit for the full task shape. Empty array returns just id. Unknown names surface in meta.warnings.WARN_UNKNOWN_FIELDS.
sortByNoField to sort tasks by: 'createdAt' (default), 'dueDate', 'modifiedAt', or 'name'. Tasks with no value for the chosen field (e.g. no dueDate) sort last.
tagIdsNoRestrict to tasks carrying ALL of these tag IDs. Get IDs from tag_list.
flaggedNotrue = flagged only; false = unflagged only; omit = all.
verboseNoWhen true, return the full unelided task shape (every field present, even at defaults). Default: false — fields equal to their documented default (flagged: false, completed: false, tagIds: [], note: null, dueDate: null, etc.) are omitted from the wire payload. An omitted field means the default applies. See docs/token-cost.md for the full defaults table.
dueAfterNoTasks with dueDate strictly after this moment. ISO-8601 with offset.
parentIdNoRestrict to direct children of this task (subtasks). Get the ID from task_get or task_list.
availableNotrue = only tasks available to work on now (not blocked, not deferred). Omit = all.
completedNo'exclude' = active tasks only; 'only' = completed tasks only; 'any' = both. Omit for adapter default.
dueBeforeNoTasks with dueDate strictly before this moment. ISO-8601 with offset (e.g. '2026-04-21T17:00:00-04:00').
projectIdNoRestrict to tasks in this project. Get the ID from project_list. Omit for all projects.
includeLinksNoWhen true, each task carries a `_links` HATEOAS block (self, project, parent, tags). Default false — the block is omitted to save payload size. Use the task's `id`, `projectId`, `parentId`, and `tagIds` fields directly instead.
updatedSinceNoReturn only tasks modified strictly after this timestamp. Accepts ISO-8601 with offset (e.g. '2026-04-21T10:00:00-07:00') or a relative shortcut: today, yesterday, this-week, next-week, end-of-week, end-of-month. Use this for incremental sync: call without updatedSince on session start, then pass the previous response timestamp on subsequent calls. Note: deleted tasks cannot be detected — use a snapshot resource for deletion detection.
sortDirectionNoSort direction: 'asc' (default, oldest/lowest first) or 'desc' (newest/highest first).
deferredBeforeNoTasks deferred until before this moment (already unlocked or soon). ISO-8601 with offset.
maxOutputBytesNoCap the serialized byte size of the returned tasks[] array. When the response would exceed this, the server returns as many whole tasks as fit, sets meta.truncatedAtCap=true with meta.bytesReturned and meta.itemsReturned, and returns a pagination cursor that resumes at the first dropped task. Omit for no cap. Values above the server's hard ceiling (~1 MiB) are clamped. A single task larger than the cap is still returned whole so pagination always advances.
notePreviewCharsNoMaximum characters of each task's note to return. Default 200. When a note exceeds this length, the response replaces `note` with `notePreview` (the truncated text), `noteTruncated: true`, and `noteLength` (full UTF-8 byte length) — fetch the full text with note_get. Pass -1 to disable truncation and return full notes inline.
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 'Returns tasks[] with pagination; safe to call repeatedly; no side effects,' which discloses key behavioral traits. However, it could be more explicit about read-only nature or potential performance impacts, but overall it is adequate.

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 concise at about 5 sentences, well-structured with purpose, usage guidelines, and examples. Every sentence is informative and none are redundant.

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 complexity (20 parameters, no output schema), the description covers purpose, usage, behavioral traits, and examples. It mentions pagination but lacks detail on return format; however, the schema and parameter descriptions fill that gap. Overall complete for a list 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 value through usage examples (e.g., task_list({ inbox: true })) and clarifies that filters like `inbox` cannot be combined with `projectId`. This goes beyond the schema's individual 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?

Description clearly states 'List tasks in OmniFocus with optional filters' and distinguishes from siblings like task_get, task_find_by_name, and search_query. It specifies the verb 'list' and resource 'tasks' with scope, making it 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?

Description explicitly states when to use this tool ('filter-based queries across tasks') and when not to, with direct alternatives for single task retrieval, name lookup, and full-text search. This provides clear guidance.

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