Skip to main content
Glama

schedule

Register a WhatsApp message to the account owner's own phone at a later time: once (at), every every_s seconds, or on a cron schedule (give exactly one). You cannot send it later yourself; tell the human the registered local time this returns. A scheduled message usually arrives outside the 24h window, so it is sent as a template and counts toward the monthly quota. The human can list and cancel from WhatsApp too: schedules, cancel <name>.

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": {
      "text": "<text>"
    },
    "name": "schedule"
  }
}

Input Schema

NameRequiredDescriptionDefault
atNoOne time: ISO 8601, e.g. 2026-11-14T09:00:00+01:00. Without an offset it is read in `timezone`. Must be in the future.
cronNoRepeat on a 5-field cron expression (minute hour day month weekday), read in `timezone`, e.g. "0 9 * * 1-5" = 09:00 on weekdays. Runs at least 15 minutes apart.
nameNoShort name (letters, digits, . _ -; up to 40) the human can cancel it by from WhatsApp; default schedule-N.
textYesThe message to send at each run (1-1024 characters), to the key owner's phone.
buttonsNoOptional reply options (up to 3); the answer arrives later via `check_replies`. Nobody waits for it.
every_sNoRepeat every N seconds (at least 900, i.e. 15 minutes).
timezoneNoIANA timezone, e.g. "Europe/Warsaw". Default: the phone country's zone (UTC when the country has several). Pass the human's zone when you know it.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so well: it discloses that scheduled messages usually fall outside the 24h window, are delivered as templates, and consume the monthly quota. It also states the return value the agent must relay (registered local time) and that button answers arrive asynchronously via check_replies with nobody waiting.

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 description is dense but front-loaded with the core action and the mode selection rule. The trailing WhatsApp-command line is secondary but still earns its place by telling the agent what to relay to the human; the wrapping and inline backticks make it slightly harder to scan than it needs to be.

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 7-parameter mutation tool with no annotations, the description covers the risky parts an agent needs: quota cost, template delivery, one-mode-only selection, and the async reply path, while the output schema handles return shape. It leaves error paths and name-collision behavior unaddressed, which keeps it short of complete.

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 per-parameter docs already carry the syntax, formats, and limits, giving a baseline of 3. The description adds a genuine cross-field constraint not expressed in the schema — exactly one of at/every_s/cron must be supplied — plus the meaning of the returned local time, lifting it above 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?

"Register a WhatsApp message to the account owner's own phone at a later time" gives a precise verb, resource, and scope, and then enumerates the three scheduling modes (at / every_s / cron). An agent immediately knows this is a delayed-send tool rather than an immediate messaging tool like the notify/ask siblings.

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 clearly constrains how to call it ("give exactly one" of at, every_s, cron) and explains the key usage decision — you cannot defer a send yourself, so register it here instead. It falls short of 5 because it never explicitly contrasts with the sibling tools cancel_schedule / list_schedules, referencing only the human-facing WhatsApp commands `schedules` and `cancel <name>`.

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.