ReminderIt

Create reminder call

create_reminder

Schedule a new reminder phone call.

This places REAL calls, so get the schedule right the first time: resolve the
timezone via whoami, and read the result back to the user afterwards.

Provide exactly one schedule: run_at (one-off), cron_expr, or interval_days.
Leave the voice arguments empty to use the account's default voice.

Args:
    title: Short label shown in the app, e.g. "Morning pills" (max 120 chars).
    message_text: Exactly what the voice says on the call, written as speech —
        "Time to take your blood pressure tablet." (max 600 chars). Avoid
        abbreviations and symbols that sound wrong when read aloud.
    type: "once" for a single call, "recurring" for a repeating schedule.
    timezone: IANA timezone the schedule is anchored to, e.g. "America/New_York".
    run_at: ISO 8601 local datetime for a one-off call. Required when type="once".
    cron_expr: Cron schedule for recurring calls, e.g. "0 8 * * 1-5" = weekdays 8am.
    interval_days: Repeat every N days (1-365). Simpler alternative to cron_expr.
    start_date: ISO date; the recurring series does not fire before this.
    end_date: ISO date; the series stops after this (e.g. end of a medication course).
    skip_dates: Local dates to skip, ["2026-08-12"] format — holidays, travel.
    recipient_id: Call a care-recipient (from list_recipients) instead of the
        account owner. The recipient must have consented.
    voice_id: Override the account voice for this reminder only (see list_voices).
    personality: Speaking style — "gentle", "cheerful", "professional", "energetic".
    language: BCP-47 language tag for the spoken message, e.g. "en-GB", "hi-IN".
    speaking_rate: Speech speed, 0.8 (slower) to 1.2 (faster). 1.0 is normal.
    whatsapp_fallback: Send the reminder on WhatsApp if the call isn't answered.
    email_fallback: Also email the reminder if the call isn't answered.

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": {
      "title": "<title>",
      "message_text": "<message_text>",
      "type": "<type>",
      "timezone": "<timezone>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "create_reminder"
  }
}

Input Schema

Name	Required	Description
`type`	Yes
`title`	Yes
`run_at`	No
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`end_date`	No
`language`	No
`timezone`	Yes
`voice_id`	No
`cron_expr`	No
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`skip_dates`	No
`start_date`	No
`personality`	No
`message_text`	Yes
`recipient_id`	No
`interval_days`	No
`speaking_rate`	No
`email_fallback`	No
`conversation_id`	No	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.
`whatsapp_fallback`	No

Output Schema

Name	Required	Description	Default
`result`	Yes
`_mcp_instructions`	No	Server-issued metadata for this conversation.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 27, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}

addedInput schema / properties / conversation_id

Added value: +{
+  "description": "Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.",
+  "type": "string"
+}

addedInput schema / properties / llm_model

Added value: +{
+  "description": "The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "title",
-  "message_text",
-  "type",
-  "timezone"
-]New value: +[
+  "title",
+  "message_text",
+  "type",
+  "timezone",
+  "context",
+  "llm_model"
+]

addedOutput schema / properties / _mcp_instructions

Added value: +{
+  "description": "Server-issued metadata for this conversation.",
+  "properties": {
+    "conversation_id": {
+      "description": "The server-issued conversation identifier.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedSep 30, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Beyond the annotations (which only state non-read-only, non-idempotent, open-world), the description discloses the highest-value behavior: this places REAL calls in the open world, so mistakes are user-visible, and it should be double-checked and confirmed afterwards. It also surfaces a prerequisite the annotations cannot express — the recipient must have consented. It does not discuss call failure/retry behavior or what the fallbacks do when the call goes unanswered beyond the one-line param notes.

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 correctly: the real-world side-effect warning and the "exactly one schedule" constraint come before the long Args list, and each arg line carries a distinct piece of information. It is long overall, but the length is justified by 20 parameters; only the closing artifact and slight verbosity in the message_text prose keep it off a perfect score.

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 20-parameter, non-idempotent, open-world create call with an output schema, the description covers the scheduling model, safety warning, consent prerequisite, and defaults (voice inheritance), which is what an agent needs to call it correctly. Minor gaps: the interaction between run_at and start_date/end_date is unstated, and the default behavior of whatsapp_fallback being true is left to the schema.

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

Parameters5/5

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

Schema description coverage is only 15%, so the description must carry the load and it does: it documents format, examples, and bounds for title (max 120), message_text (max 600, written as speech), run_at (ISO 8601 local), cron_expr (with an example), interval_days (1-365), start_date/end_date roles, skip_dates format, personality values, language (BCP-47), and speaking_rate range. The only parameters it omits (context, llm_model, conversation_id) already have rich schema descriptions.

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 opening line states a specific verb and resource ("Schedule a new reminder phone call") and the body makes clear it creates a live outbound call, which cleanly separates it from siblings like test_call, preview_voice, or update_reminder. An agent can identify the operation without opening the schema.

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?

Gives concrete operating guidance: resolve the timezone via whoami first, read the result back to the user, supply exactly one schedule field, and leave voice args empty for the account default. It also routes to list_recipients and list_voices for dependent IDs. It stops short of explicitly naming when to use a sibling instead (e.g. test_call before committing to a real reminder, or update_reminder for changes).

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

All ReminderIt tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?