Skip to main content
Glama

Prepare or send a payment reminder

send_reminder
Destructive

Use this when the user asks to remind a client to pay, chase an unpaid or overdue invoice, or send a payment reminder. Sends the client a payment reminder for an issued unpaid invoice, exactly as Fatura Go's own reminder (same template and wording, amount due, link to the invoice). Two steps: without confirmation_token nothing is sent and the result is a preview (invoice, client, amount due, channel, masked recipient, the exact message) with a confirmation_token valid 10 minutes for one use; call again with the same arguments and the token only after the user answered (a confirmation sent within 10 seconds of the preview is refused). Not for a Shopify order's invoice. Email when the client has one. When the client has only a phone, Fatura Go sends nothing: the confirmed result is a WhatsApp link with the message for the user to open. At most one reminder per invoice per 24 hours from an assistant. Needs the send permission. Do not use it to send a new invoice or a statement: those are sent from Fatura Go.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "send_reminder"
  }
}

Input Schema

NameRequiredDescriptionDefault
invoice_idNoFrom list_invoices or get_invoice.
business_idNoFrom list_businesses. May be left out: the invoice is then looked up in every business shared with this connection.
template_idNoA payment reminder template of the business, when the user picked one. Default: the template the app would use.
invoice_numberNoInstead of invoice_id.
confirmation_tokenNoLeave out on the first call (preview). Pass the token from the preview only after the user confirmed it, with the same other arguments.

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?

The description goes well beyond the annotations: two-step preview/confirm flow, token validity of 10 minutes and single use, refusal of a confirmation within 10 seconds of the preview, a 24-hour per-invoice rate limit, a required send permission, and the WhatsApp-link fallback when the client has no email. These match the destructiveHint/openWorldHint/idempotentHint=false annotations rather than contradicting them.

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 trigger condition is front-loaded and most sentences carry distinct operational facts (preview contents, token rules, WhatsApp fallback, rate limit). It is long and slightly dense in the middle, with some overlap between the opening trigger and the purpose sentence, but there is little pure filler.

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?

For a destructive, open-world send tool with no output schema, the description covers what the preview returns (invoice, client, amount due, channel, masked recipient, exact message), what the confirmed result is, and all the gating conditions. An agent has everything needed to execute the two-step flow correctly.

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 adds real meaning by explaining that confirmation_token must be replayed with identical arguments and why (the 10-second and 24-hour guards). It says nothing about business_id omission or invoice_number vs invoice_id, so it does not fully cover every parameter.

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 concrete verb+resource (sends a payment reminder for an issued unpaid invoice) and explicitly demarcates it from siblings: not a Shopify order's invoice, not a new invoice, not a statement. An agent can route between send_reminder and prepare_invoice/get_client_statement 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?

It states the exact triggering user intents (remind a client to pay, chase an unpaid or overdue invoice) and gives explicit exclusions ('Not for a Shopify order's invoice', 'Do not use it to send a new invoice or a statement'). It also supplies the preconditions for the second call, so the agent knows the full call sequence.

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