Familia

Create task

familia_create_task

Destructive

Use this when the user asks to create a responsibility-style Familia task, agreement, reminder, or chore. If the same task repeats across several days, weeks, or months, provide repeatRule and create one recurring task instead of multiple one-time tasks. Do not use for calendar-style events, trips, school activities, or holidays; use familia_create_plan instead. When the primary intent is a shopping list, packing list, or standalone checklist, use familia_create_list_task. Assigning to another household member queues a push notification; schedules can also queue reminders, and delivered notifications cannot be recalled.

Input Schema

TableJSON Schema

Name	Required	Description
`dueAt`	No	Accepts YYYY-MM-DD for all-day items or an RFC 3339 datetime. When using a datetime without an offset, provide timezone.
`title`	Yes	Short task title, e.g. "Pay school fee" or "Take bins out".
`allDay`	No	Whether the due date is an all-day task.
`timezone`	No	IANA timezone for dueAt, e.g. Europe/Prague.
`todoList`	No	Optional checklist/list to attach to the created task.
`repeatRule`	No	Optional RFC 5545 RRULE, e.g. FREQ=DAILY;INTERVAL=2 or FREQ=WEEKLY;BYDAY=MO,WE. Use this when the user says the same task or plan repeats across days, weeks, or months; create one recurring schedule instead of multiple one-time items unless each occurrence has different content. Requires the first dueAt/startAt as the anchor.
`description`	No	Optional task details, notes, or context.
`householdId`	Yes	Familia household id where the task should be created.
`leadMinutes`	No	Reminder lead time in minutes before dueAt. Defaults to 0.
`ownerUserId`	No	Optional Familia user id that owns the task.
`assigneeUserId`	No	Optional Familia user id responsible for the task.
`idempotencyKey`	No	Optional stable retry key. Reusing the same key for the same create operation returns the original result instead of creating a duplicate.
`recurrenceEndDate`	No	Optional YYYY-MM-DD end date for a recurring schedule. Use this for bounded repeats such as "this week", "for three days", or "until Sunday".

Output Schema

TableJSON Schema

Name	Required	Description	Default
`taskId`	No
`deeplink`	Yes
`schedule`	No
`agreementId`	Yes
`attachmentError`	No
`attachmentCreated`	No
`todoListAttachment`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, and the description adds valuable behavioral context: assigning to another member queues a push notification, schedules can queue reminders, and delivered notifications cannot be recalled. This goes beyond the annotation and informs the agent of side effects and irreversibility, though it does not enumerate all possible side effects (e.g., what happens to subtasks or attachments).

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 compact yet information-dense: it front-loads the primary purpose, then adds recurrence guidance, exclusions, alternatives, and notification behavior in four sentences with zero fluff. Every sentence earns its place and the structure aids quick parsing.

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?

For a tool with 13 parameters, nested objects, and an output schema, the description covers the most critical decisions: when to use this tool, when to route to siblings, recurrence handling, and notification side effects. It does not describe return values, but the output schema covers that. It could mention required fields (householdId, title) but these are in the schema, so completeness is high but not maximal.

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 adds a little extra meaning by explaining that repeatRule is used for recurring schedules and that assigneeUserId triggers a notification, but these are already partially implied in the schema. It does not add new syntax or format details beyond the schema, so it stays at baseline.

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 opens with a specific verb+resource (create a responsibility-style Familia task, agreement, reminder, or chore) and immediately distinguishes itself from sibling tools by naming the alternatives (familia_create_plan for calendar events, familia_create_list_task for checklists). This leaves no ambiguity about the tool's core purpose.

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?

Explicit guidance covers both when to use (responsibility-style tasks) and when not to use (calendar events, trips, school activities, holidays, shopping lists, packing lists, standalone checklists), naming the exact sibling tools to route to instead. It also gives recurrence policy (use repeatRule for repeating tasks) and notes side effects of assignee assignment, so an agent knows the right conditions to invoke this tool.

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

All Familia tools Inspect

Try in Browser

Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?