Skip to main content
Glama

Update a routine

update_routine
DestructiveIdempotent

Change ONE routine by id (from get_routines): rename it, move its start time, set per-weekday times or days, change its length or steps, or switch it on or off. Only the fields you send change. steps REPLACES the whole list (send every step in order); addSteps and removeSteps edit it. When steps change, the length follows them unless durationMin is sent. Use update_task for tasks that are not routines, and delete_task with a date to skip a routine for one day. Editing the built-in morning or evening routine also switches it on. Returns {ok:true, id, title, hour, minute, durationMin, steps, daysOfWeek, enabled?}; ok:false (not_found, not_a_routine, title_taken, reserved_title, invalid_args) changed nothing. 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_routine"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe routine id from get_routines, e.g. "routine_morning".
hourNoNew usual start hour, 0-23 local time.
stepsNoThe COMPLETE ordered step list - REPLACES every step (read them with get_routines first). Use removeSteps to drop steps.
titleNoRename it; same routine, time, steps and reminders.
minuteNoNew start minute, 0-59 (default 0 when hour is sent).
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.
enabledNofalse = switch it off (hidden from the schedule, no reminders, steps and history kept); true = switch it back on.
addStepsNoSteps to append at the end, e.g. [{"name":"Stretch","durationMin":5}]. Ignored with steps.
dayTimesNoA different start time on some weekdays; hour/minute stay the usual time. List only the days that differ, e.g. [{"weekday":6,"hour":9}] for 9:00 on Saturdays. Replaces earlier per-day times; [] = one time every day.
daysOfWeekNoWeekdays it runs on, 1=Monday .. 7=Sunday, e.g. [1,2,3,4,5] for weekdays only. Omit (create) or [] (update) for every day.
durationMinNoNew length in minutes, 5-180. Omitted when steps change: the length follows the steps.
removeStepsNoNames of steps to remove (case-insensitive), e.g. ["Stretch"]. Ignored with steps.

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 already declare destructiveHint=true and idempotentHint=true, but the description goes further: it discloses that steps fully REPLACES the list while addSteps/removeSteps are ignored when steps is sent, that length follows steps unless durationMin is given, and that editing the built-in morning/evening routine switches it on. It also documents the return payload and every failure code (not_found, not_a_routine, title_taken, reserved_title, invalid_args) with the guarantee that failures changed nothing.

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 purpose is front-loaded in the first clause, followed by mutation semantics, sibling routing, return shape, and the preview rule in a logical order. It is dense and a few clauses duplicate schema wording (steps replacement, ignored-with-steps), which costs a point but no sentence is filler.

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 12-parameter destructive mutation with no output schema, the description supplies everything an agent needs: what persists, what gets replaced, side effects on built-in routines, the confirm/preview gate, and the full success and error result shape. Nothing material is left to inference.

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 the baseline is 3; the description earns an extra point by explaining cross-field interactions the schema only states piecemeal — "Only the fields you send change," steps overriding addSteps/removeSteps, and durationMin being ignored when steps change. Some of this restates schema text ("REPLACES every step," "Ignored with steps"), so it is additive rather than wholly new.

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?

"Change ONE routine by id (from get_routines)" gives a specific verb, resource, cardinality constraint, and the source of the identifier. It then enumerates the concrete changeable facets (rename, start time, per-weekday times/days, length, steps, on/off), so the agent knows exactly what this tool covers 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?

It explicitly routes away from the tool twice: "Use update_task for tasks that are not routines" and "delete_task with a date to skip a routine for one day," distinguishing a one-day skip from a permanent change. It also states the preview/confirm workflow condition (second change within ~90 seconds) that governs when the call can actually persist.

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