Skip to main content
Glama

Create schedule

create_schedule
Destructive

Send the same text to one number every day, week or month at a local time (e.g. a weekly reminder). Every occurrence runs the usual send checks.

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": {
      "to": "<to>",
      "body": "<body>",
      "repeat": "<repeat>"
    },
    "name": "create_schedule"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesRecipient's number in E.164
bodyYesThe text sent each time
fromNoOne of your numbers. Optional when the account has exactly one number for the key's mode.
repeatYesWhen it sends: how often, the local time and the time zone
categoryNoOptional. It can make each occurrence stricter (`marketing`), never looser: the sending number's registration and the wording decide ([which messages are marketing](/docs/compliance-checks#which-messages-are-marketing)).
end_dateNoLast local date it may run (inclusive).
start_dateNoFirst local date it may run. Defaults to today.
quiet_hoursNoOptional. What to do with a message in the recipient's quiet hours: `block` refuses it (403 quiet_hours), `defer` holds it until their next 9:00am. Omitted: an occurrence in quiet hours is held until the recipient's 8:00am and recorded as `deferred`.
idempotency_keyNoOptional. Retries are already safe: the same call with the same inputs within 10 minutes is done once and answers with the first result. Pass your own key to dedupe across a longer gap, or a new one to repeat an identical call on purpose.
max_occurrencesNoThe schedule completes after this many messages have been sent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / quiet_hours / description
      Previous value: -"Optional. What to do with a message in the recipient's quiet hours: `block` refuses it (403 quiet_hours), `defer` holds it until their next 8:00am. Omitted: an occurrence in quiet hours is held until the recipient's 8:00am and recorded as `deferred`."New value: +"Optional. What to do with a message in the recipient's quiet hours: `block` refuses it (403 quiet_hours), `defer` holds it until their next 9:00am. Omitted: an occurrence in quiet hours is held until the recipient's 8:00am and recorded as `deferred`."
  2. Changed4 schema fields changed
    • addedInput schema / properties / body / description
      Added value: +"The text sent each time"
    • addedInput schema / properties / repeat / description
      Added value: +"When it sends: how often, the local time and the time zone"
    • addedInput schema / properties / repeat / properties / frequency / description
      Added value: +"How often it sends"
    • addedInput schema / properties / to / description
      Added value: +"Recipient's number in E.164"
  3. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is carried structurally. The description adds real value with 'Every occurrence runs the usual send checks', telling the agent that per-occurrence compliance gates apply. It does not disclose that each occurrence bills as a message, nor how to stop the series (delete_schedule/update_schedule), which is notable for a destructive recurring tool.

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?

Two short sentences, front-loaded with the core action and cadence, then the compliance caveat. Nothing is wasted and nothing important is buried.

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 10-parameter tool with a nested object, the schema is fully documented and annotations cover safety, so the description need not restate parameters or return values. The only real gap is operational context about cost per occurrence and lifecycle management, which is a minor omission against the otherwise rich structured data.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and every parameter, including the nested repeat object and enums, is documented in the schema. The description only reinforces that there is exactly one recipient and one repeated body, adding no syntax or format detail beyond the schema. Baseline 3 applies.

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 gives a concrete verb and scope: send the same text to one number on a daily/weekly/monthly cadence at a local time, with a reminder example. That clearly separates it from one-off send_message. It does not, however, distinguish it from create_automation, the other recurring-send sibling, which an agent could plausibly confuse it with.

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

Usage Guidelines3/5

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

The 'e.g. a weekly reminder' example implies the intended use case, but there is no explicit when-to-use/when-not guidance and no named alternative (send_message for one-off, create_automation for event-triggered flows). The agent must infer the routing decision.

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.