Skip to main content
Glama

Update a task

update_task
DestructiveIdempotent

Change ONE existing task by id (from get_tasks): time, date, title, duration, done, repeat, steps, checklist, priority, alert type and more. Only the fields you send change. Use it to move, rename or tick off a task; use delete_task to remove it and update_routine for a routine. On a repeating task, hour/min/date move EVERY day; occurrence_date moves one day and done_date ticks one day. subTasks and checklist REPLACE the whole list (send every item). Returns {id, updated, ...}; ok:false or an error such as not_found means nothing was saved. Preview rule: if this is the second task or routine change within about 90 seconds, nothing is saved and the result is needs_preview with the pending and saved changes - show them to the user and call again with confirm:true only after they agree.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "id": "<id>"
    },
    "name": "update_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe task id from get_tasks, e.g. "aB3dE9". A repeating task's projected id (<id>_recur_YYYYMMDD) also works.
minNoNew start minute, 0-59 (default 0 when hour is sent).
dateNoMove the task to this date, YYYY-MM-DD. On a repeating task this moves the whole series; for one day use occurrence_date.
doneNoMark the task done (true) or not done (false). On a REPEATING task this is ONE day: the projected id's day (<id>_recur_YYYYMMDD), else today - pass done_date for another day, never `date`.
hourNoNew start hour, 0-23 local time (send min too; default 0).
titleNoNew title.
allDayNoMake it an all-day event (true) or a timed task (false).
repeatNoChange how the task repeats. Once->recurring keeps its current date as the series origin; recurring->Once keeps past per-day completions but stops future occurrences. Edits IN PLACE - never delete+recreate. One of: Once | Daily | Weekly | Monthly | Yearly.
anytimeNoFlexible anytime task (true) vs fixed-time (false).
confirmNoSet true ONLY after the user has seen and approved this change in a preview you showed them (needed when a request changes more than one task or routine). Never set it on your own. Default false.
contextNoChange the task type/context tag. One of: calls | commute | errands | deep.
categoryNoNew category label, e.g. Work or Health.
priorityNoPriority: 4 Very High, 3 High, 2 Medium, 1 Low; 0 clears it. Only when the user re-prioritizes.
subTasksNoREPLACE the task's steps with this COMPLETE ordered list (read the current steps with get_tasks first and send the whole edited list, unchanged steps included). An EMPTY array removes all steps. A step that keeps its name keeps its done tick. On a REPEATING task the steps change for EVERY day.
checklistNoThe task's "Bring / prep" checklist - things to bring or have ready ("bring the contract to my meeting with Ash"). REPLACES the list with this COMPLETE list: read it with get_tasks first and send every item, unchanged ones included. An item that keeps its text keeps its tick. An EMPTY array removes the list. Never put these items in the description or the steps.
day_timesNoA STANDING per-weekday time: set a DIFFERENT start time on some weekdays of a REPEATING task, EVERY week from now on ("Tuesdays at 5:15, other days 7:30"). List only the days that differ from its usual time; REPLACES any earlier per-day times. Pass an EMPTY array [] to go back to one time every day. NEVER for one date ("just for today", "only this Saturday", "just this once", "back to normal tomorrow"): weekday 6 moves EVERY Saturday. For one day use occurrence_date.
done_dateNoYYYY-MM-DD: the DAY a done / not-done is for on a REPEATING task ("I did yesterday's workout" -> yesterday). Defaults to the projected id's day, else today. Must be a day the task happens on, never in the future. NEVER pass `date` for this - on a repeating task `date` moves the whole series.
alert_typeNoChange how the reminder fires: "alarm" | "push" | "default" (clear the override).
daysOfWeekNoSet SPECIFIC weekdays (1=Monday..7=Sunday) the task repeats on, e.g. [1,2,3,4,5] for weekdays only. Pass an EMPTY array [] to CLEAR back to the plain cadence. Only meaningful on a recurring task (repeat is coerced to Weekly when needed).
descriptionNoSet or replace the task detail (a number, an address, a reference, a note). Pass an EMPTY string to clear it. It REPLACES what is there - to add to an existing note, read the task first and send the combined text.
durationMinNoNew length in minutes, e.g. 45.
in_progressNotrue when the user says they are STARTING / doing this task NOW. Records the start; never re-times the task - do not pass hour/min with it.
contact_nameNoSet/replace who a CALL task is to.
delegated_toNoThe NAME of the person who covers this task instead of the user ("my wife will do the pickup" -> "Wife"); "" = the user does it again. A delegated task never counts as an overlap and gets no start reminder. "Assindo" is the built-in delegate - the user's AI phone assistant app: it makes the phone call or posts to social media for this task. Use delegated_to "Assindo" only when the user asks Assindo to do it; Habidu sends it the task when it is saved (it needs Assindo connected in Settings - Connected apps).
restore_dateNoYYYY-MM-DD: bring back ONE skipped day of a REPEATING task (a day get_tasks lists under `skipped`). Takes that day off the task's excluded days; nothing else changes. Only when the user wants it back on that day.
alarm_missionNoA MISSION that must be done before this ALARM stops ringing (Android and iPhone): "math" = solve math problems, "shake" = shake the phone, "steps" = walk a number of steps, "qr" = scan a QR code / barcode the user registered in Settings > Reminders & alarms > Mission codes. "none" removes it. Setting a mission makes the task an alarm. Set it ONLY when the user explicitly asks ("make me solve math to turn it off", "an alarm I have to shake to stop", "make me walk 200 steps"). Never unprompted.
contact_phoneNoSet/replace the phone number for a CALL task, as the user gave it — NEVER invent one.
checklist_dateNoYYYY-MM-DD: the DAY a checklist_tick / checklist_untick is for on a REPEATING task ("packed the gym bag for tomorrow" -> tomorrow's date). Defaults to today. NEVER pass `date` for this - on a repeating task `date` moves the whole series.
checklist_tickNoItem TEXTS (from get_tasks checklist) the user says they have ready / packed - ticks them. On a repeating task only the asked day.
delegated_dateNoYYYY-MM-DD: the day a one-day delegation is for (default: the occurrence id's day, else today).
delegated_scopeNoWith delegated_to on a REPEATING task: "occurrence" (the default) hands over ONE day only ("Mom takes the kids today"); "series" = every day, ONLY when the user says always / every time / from now on.
occurrence_dateNoYYYY-MM-DD: move ONLY this one day of a REPEATING task or routine ("just for today", "tonight only", "only this Saturday", "back to normal tomorrow"). Send it with the new hour/min (and durationMin if the length changes): that day becomes its own one-off at the new time and the usual time is skipped that day; every other day keeps its time. One call per task. Never day_times or `date` for a one-day move.
checklist_untickNoItem TEXTS to untick again (the user does not have them after all).
alarm_mission_countNoHow many problems (math, 1-10, default 3), shakes (shake, 10-100, default 30) or steps (steps, 20-1000, default 100). Only with alarm_mission.
alarm_mission_levelNoMath difficulty: easy | medium (default) | hard. Only with alarm_mission "math".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare a destructive, idempotent write, and the description adds substantial context beyond them: partial-update semantics ('Only the fields you send change'), list-replacement semantics for subTasks/checklist, the repeating-task split between series-wide fields and single-day fields, the return shape, and the failure contract ('ok:false ... means nothing was saved'). The preview rule ('nothing is saved and the result is needs_preview ... call again with confirm:true') is behavior no annotation could convey.

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?

Front-loaded with purpose, then sibling routing, then the tricky recurrence semantics, then the return/failure contract and preview rule. It is a dense block rather than sectioned, which slightly hurts scanability for a 35-parameter tool, but nearly every sentence carries information an agent needs.

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?

For a 35-parameter mutation tool with no output schema, the description covers the return value, the failure signal, the confirm/preview protocol, and the highest-risk ambiguity (recurring vs one-day edits). Nothing essential to calling it correctly is absent.

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 description coverage is 100%, so the baseline is 3; the description earns above that by explaining cross-parameter interactions the schema states only in isolation (hour/min/date move the whole series while occurrence_date moves one day, done_date ticks one day). The enumerated field list is illustrative ('and more') rather than exhaustive, which is acceptable given the schema.

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?

States a specific verb and resource ('Change ONE existing task by id (from get_tasks)'), enumerates the mutable fields, and explicitly distinguishes itself from delete_task and update_routine. An agent can identify this as the partial-update tool for a single task without opening the schema.

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?

Gives concrete use cases ('move, rename or tick off a task') and names the alternatives with their conditions ('use delete_task to remove it and update_routine for a routine'). It also prescribes the exact two-step preview/confirm workflow, so the agent knows not just when to call but how to sequence calls.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources