Skip to main content
Glama

task_schedule

Schedule an instruction to execute at a future time and deliver the result to your chat, solving delayed-action tasks instead of reminders.

Instructions

Run an instruction later and send the answer to a paired chat.

Use this, not a reminder, when the user wants something done at a time rather than something said: "check the order at 3 and text me" has no message to deliver yet, because the answer does not exist until the work runs. A reminder would just hand the task back to them.

When it comes due the instruction is queued as an ordinary agent turn, so the reply arrives looking exactly like any other answer. Never schedule this kind of work in your own runtime's cron: Alfred owns schedules and delivery here, and a job elsewhere silently never fires.

run_at is ISO-8601 with an offset. daily repeats it, and then timezone must be an IANA name (America/New_York) so the task keeps its local hour across a daylight-saving change. When Hermes is answering an inbound Telegram turn, chat_id may be omitted and is read from ALFRED_TELEGRAM_CHAT_ID.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dailyNo
promptYes
run_atYes
chat_idNo
timezoneNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only say it's not read-only and not destructive. The description goes far beyond: it explains that the instruction is queued as an ordinary agent turn ('the reply arrives looking exactly like any other answer'), warns that a job elsewhere silently never fires, and details the chat_id fallback behavior from ALFRED_TELEGRAM_CHAT_ID. It also clarifies daily/timezone handling. This is rich behavioral context not present in the schema or annotations.

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?

Though longer than typical, every sentence earns its place. The core action is stated first, then the critical distinction from reminders, then behavior, then parameter notes. No fluff or redundancy; the structure front-loads the most decision-relevant information.

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?

The description is complete for a scheduling tool: it covers what it does, when to use it, how the execution works, parameter formats, special cases (Telegram chat_id fallback), and a critical operational warning. No output schema exists, but that is not needed for a fire-and-forget scheduling action. Nothing essential is missing.

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 0%, so the description must explain parameters. It does well for the non-obvious ones: run_at must be ISO-8601 with offset, daily repeats it and then timezone must be IANA, chat_id may be omitted under a specific condition. It does not explicitly state that prompt is the instruction to run, but that is inferable from the tool's purpose and description. It adds significant meaning beyond the bare 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?

The description opens with a clear verb–resource pair: 'Run an instruction later and send the answer to a paired chat.' It immediately distinguishes itself from the sibling reminder_set by explaining when to use scheduling over a reminder ('when the user wants something *done* at a time rather than something *said*'), and gives a concrete example. This makes it impossible for an agent to confuse it with other tools.

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?

The description provides explicit when-to-use guidance ('Use this, not a reminder...'), a concrete example, and a strong when-not-to-use instruction ('Never schedule this kind of work in your own runtime's cron'). It also explains the alternative (a reminder) and why it would be inappropriate, leaving no ambiguity about selection.

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