Skip to main content
Glama

send_test_otp

Sends a one-time verification code by SMS or email in test mode to trial login/2FA; unconfirmed recipients stay in the sandbox, and results include test_code when available.

Instructions

Send a one-time verification code (OTP) by SMS or email to a phone number in Israel using Otipi, in test mode. Use this to try the login/2FA flow end to end. With a test key the message really arrives ONLY if the recipient was confirmed with add_test_recipient + confirm_test_recipient; otherwise it is kept in the sandbox log and nothing is delivered. The result says which case happened and includes test_code when available, so you can verify it with verify_otp. Each account has 5 free test SMS for life.

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>",
      "app": "<app>"
    },
    "name": "send_test_otp"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesIsraeli mobile number in E.164 format +9725XXXXXXXX (05XXXXXXXX is also accepted), or an email address for the email channel.
appYesBrand name shown in the message, for example "MyApp". Max 40 characters.
channelNoDelivery channel. Default sms.sms
languageNoMessage language. Default he (Hebrew).he

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does most of it: it explains the sandbox fallback (message kept in the sandbox log, nothing delivered), the quota ('5 free test SMS for life'), and what the result contains ('which case happened and includes test_code'). It stops short of covering quota-exhaustion or error behavior for invalid recipients.

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?

Purpose is front-loaded in the first clause and every sentence carries information. The middle is a dense run of conditional clauses, but none are filler.

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?

No output schema exists, and the description compensates by describing the result shape (case plus test_code). For a send operation with no annotations, the only real gap is failure/quota-exhaustion behavior.

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 coverage is 100% and all four parameters are already documented in the schema, including the E.164 format and enum defaults, so the description adds little. It does reinforce the Israeli-number restriction and the email channel, but that meaning is already in the schema.

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?

States a specific verb and resource ('Send a one-time verification code (OTP) by SMS or email'), names the provider (Otipi), and pins the mode ('in test mode') so it is unambiguous against verify_otp or the recipient-management siblings.

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 about intent ('try the login/2FA flow end to end'), about the precondition that selects real delivery ('ONLY if the recipient was confirmed with add_test_recipient + confirm_test_recipient'), and about the natural follow-up ('verify it with verify_otp').

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