Skip to main content
Glama

Send approved bulk SMS

spur_send_bulk_sms
Destructive

Queue the exact approved message and recipient set, including mapped CSV rows. Show the text, audience and segment cost first. Requires recipient consent; a clear DNC result does not establish opt-in. Never automatically retry a timed-out send.

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": {
      "message": "<message>",
      "recipients": "<recipients>",
      "confirm": "<confirm>"
    },
    "name": "spur_send_bulk_sms"
  }
}

Input Schema

NameRequiredDescriptionDefault
fromNo
confirmYesSet to true ONLY after the user explicitly approved this exact action in the conversation. Never assume approval.
messageYes
variablesNo
recipientsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already flag destructive, non-idempotent, open-world behavior, and the description adds genuinely useful context: consent/opt-in obligations, the caveat that a clean DNC check is not opt-in, and the explicit instruction not to retry a timed-out send (a direct consequence of non-idempotency). It stops short of describing credit charging mechanics, partial-failure behavior, or what a queued send returns.

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?

Four short sentences, each doing distinct work: purpose, pre-send preview, consent rule, retry rule. No filler and the operational constraints are front-loaded after the action statement.

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 destructive, non-idempotent send tool with no output schema and a nested recipient array, the definition covers the highest-risk behaviors (approval, consent, cost disclosure, retries). It is slightly thin on parameter-level meaning for 'from'/'variables' and on what the tool returns after queuing.

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 only 20% across 5 params (one nested), so the description must compensate: it clarifies that recipients must be the approved set with mapped CSV row data, implying the variables/row-mapping relationship. It says nothing about 'from' or the 'confirm' flag beyond the schema's own text, so coverage remains incomplete.

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?

States a specific verb (queue/send) and resource (bulk SMS) with scope: the exact approved message and recipient set, including mapped CSV rows. It implicitly separates itself from single-send siblings via 'bulk' and 'approved', but never names spur_send_sms or spur_send_test_email as alternatives.

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 clear procedural preconditions — show the text, audience and segment cost first; require recipient consent; never auto-retry a timed-out send. It does not route the agent between siblings (e.g., single SMS vs bulk) or state when bulk is inappropriate, which keeps it short of a 5.

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