Skip to main content
Glama

WA MCP

schedule_message

Schedules a WhatsApp message (text, or a file with optional caption) to one person or group for a later time, once or repeating (e.g. "every Monday at 9:00"). Paid plan only: on the free plan the call is refused with a note on how to subscribe. to works like send_message's and is resolved now, so a wrong name fails right away. Time: pass send_at as an ISO 8601 date-time with the user's UTC offset for that date (e.g. "2026-10-10T09:00:00-06:00"), and timezone as the user's IANA timezone (e.g. "America/Mexico_City"). Use the timezone and current time you know for the user; if you don't know them, ask. Mind daylight saving time: the offset must be the one in effect on that date. The first send must be in the future and at most a year ahead. Messages go out within about a minute of send_at; if the server is down for more than an hour past send_at, that send is marked missed instead of being sent late. Repeats: recurrence once (default), daily, weekly, biweekly, monthly, quarterly, semesterly or yearly, always at the same local time (a monthly message on the 31st goes on the last day of shorter months); optional until (a date like "2026-12-31", or a date-time with offset) ends the series. Each send is tried once: a failure is recorded (see list_scheduled_messages) and the series continues. Quoted replies aren't supported. Files: media.url or media.message_id (checked now and fetched again at send time; message_id only for one-off messages, so prefer a link); media.data isn't accepted. The result gives the local time and how long until it (when) and, for repeats, the first sends: read them back to the user. To change a scheduled message, cancel it with cancel_scheduled_message and schedule it again. At most 100 upcoming scheduled messages per account. If you are writing the text yourself rather than sending words the user gave you, call get_writing_style for this chat first and write it the way the user writes; skip that for dictated text. To protect the user's number from WhatsApp's anti-spam bans, messages that start a conversation with someone who hasn't messaged the user in the last 90 days may be limited to 1 per minute and 10 every 12 hours; the result says so and explains why when it happens. People who have written to the user are never limited. Confirm the recipient, text, file and time with the user first unless they already gave them. Returns the scheduled message { id, series_id (shared by every send of a repeating message), status (scheduled, processing, sent, failed, missed or cancelled), recipient (contact fields (name; name_source: address_book, push_name, group_subject, business, phone or unresolved; canonical_jid: the JID to pass to send_message and read_chat_history; phone_jid and lid_jid: the chat's phone-number and LID forms, null when unknown or for groups; phone_display: the number as +).), text?, media?, send_at (UTC), send_at_local, when (readable local time and how far away), timezone, recurrence, occurrence? (0 = first send of a series), until?, sent_at?, message_id? (once sent), error? (why it failed or was missed) } plus next_occurrences for repeats.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toYesContact name, phone number with country code, chat JID (person or group), or a group's exact name.
textNoThe message text. With media, the caption of a photo, video or document. Required unless media is given.
mediaNoOptional. A file to send: pass exactly one of url or message_id. The file is fetched when the message is sent.
untilNoOptional, repeats only. Last day of the series: a date ("2026-12-31", through the end of that day) or a date-time with offset.
send_atYesWhen to send (the first send, for repeats): ISO 8601 with the UTC offset in effect on that date, e.g. "2026-10-10T09:00:00-06:00".
timezoneYesThe user's IANA timezone, e.g. "America/Mexico_City". Repeats keep the same local time in it, across daylight saving changes.
recurrenceNoOptional. How often to repeat (default once).

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 only mark this as a non-read-only, non-idempotent write; the description goes far beyond that with operational detail an agent cannot get elsewhere: 100 upcoming messages per account, one-hour late-send window then marked 'missed', per-send failure recording with series continuation, anti-spam throttling for cold contacts (1/min, 10/12h) and the fact that inbound-writers are never limited, and file re-fetch at send time.

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 the purpose and every sentence carries real information (limits, DST, throttling, return shape). The weakness is form: one long unbroken paragraph that mixes usage rules, timezone guidance, recurrence semantics and an inline return-object spec, so it is harder to scan than it needs to be for a tool this heavily used.

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?

No output schema exists, and the description compensates by enumerating the returned fields (id, series_id, status values, recipient fields, send_at_local, when, occurrence, error) plus next_occurrences, and instructs the agent to read the times back to the user. For a tool with nested media params, enums and recurring-series state, nothing an agent needs to call or report correctly 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 coverage is 100%, so the baseline is 3; the description compensates for the harder parameters by adding rules the schema does not: the offset must be the one in effect on the target date (DST), the first send must be in the future and within a year, monthly-on-the-31st rolls to the last day, and `until` accepts a bare date or an offset date-time. It does not add syntax detail for `to` beyond what the schema already says.

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?

Opens with a specific verb+resource ('Schedules a WhatsApp message ... to one person or group for a later time, once or repeating') and immediately distinguishes it from send_message by naming `to` resolution and from cancel_scheduled_message by pointing to that tool for changes. An agent can tell exactly what this tool does versus its siblings without opening any 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?

Explicit when-to-use rules: paid plan only (and what happens on free), confirm recipient/text/file/time first unless already given, call get_writing_style only when composing text rather than relaying dictated words, and change a schedule by cancelling and re-scheduling. It also states exclusions ('Quoted replies aren't supported') and alternatives for file input ('prefer a link').

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