Skip to main content
Glama

Set Task Lock

set_task_lock
Idempotent

Change Task Lock on the user's iPhone/iPad: turn it on or off, set the time of day it starts locking, whether timed tasks only count once their time has come (onlyDueByNow), allow 15-minute breaks, or pick which saved app list it blocks. Only pass what changes. Task Lock blocks the apps in the active list until the tasks that count are done; which apps are in a list can only be chosen in Weeklane on the phone. Turning it off unblocks the apps right away, so only do that when the user asks. The phone applies the change as soon as it receives it. Can be reverted with undo_last_change.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

NameRequiredDescriptionDefault
listIdNoId of a saved app list from get_task_lock (instead of the name).
enabledNotrue = Task Lock on, false = off.
listNameNoName of a saved app list, e.g. "Social" (case-insensitive).
breakEnabledNoAllow the user to take 15-minute breaks from the lock.
onlyDueByNowNotrue = a task with a time only counts once its time has come; false = all of today's tasks count.
lockStartMinutesNoTime of day the lock starts (device time): "HH:MM" (e.g. "09:00") or minutes after midnight (540). null = lock all day.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations only declare the mutation profile (not read-only, idempotent, non-destructive); the description goes well beyond them by stating that the phone applies the change immediately, that disabling unblocks apps right away, that list membership can only be edited on the phone, and that the change is revertible with undo_last_change. This is exactly the operational context an agent needs before mutating a user's device state.

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?

It is front-loaded with the action and the settable fields, then layers constraints and side effects in a sensible order. A couple of clauses are slightly redundant ('the tasks that count are done' repeats the onlyDueByNow idea), but nearly every sentence carries operational weight.

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 six-parameter, all-optional mutation with no output schema, the description covers the important ground: partial updates, immediate device application, the irreversible-feeling consequence of disabling, and recovery via undo_last_change. Only the relationship to switch_task_lock_list and listId/listName precedence are left unexplained.

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 the real-world consequence of the fields ('Task Lock blocks the apps in the active list until the tasks that count are done') and by reinforcing the listId-vs-listName distinction and the onlyDueByNow semantics. It does not, however, say how a conflict between listId and listName is resolved.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Change Task Lock on the user's iPhone/iPad') and enumerates the exact settings it can change (on/off, start time, onlyDueByNow, breaks, blocked list). It is easy to distinguish from get_task_lock and undo_last_change, but it never clarifies how 'pick which saved app list it blocks' differs from the sibling switch_task_lock_list, leaving one genuine ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit partial-update guidance ('Only pass what changes') and an explicit when-not ('Turning it off unblocks the apps right away, so only do that when the user asks'), plus the revert path via undo_last_change. The only gap is that it does not say when to prefer switch_task_lock_list over setting listId/listName here.

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