Skip to main content
Glama

WhaTools — WhatsApp tools

by tools.wha
OverviewDiscussionsAdmin

estimate_whatsapp_api_cost

Estimate the monthly WhatsApp Business (Cloud) API cost under Meta's per-message pricing (in effect since 1 July 2025). Given a country/market and monthly volumes of marketing, utility, authentication and (optionally) service messages, returns an itemized breakdown and total in USD. Marketing is always billed; utility and authentication are billed with volume-tier discounts in many markets. As of 1 October 2026 utility is billed even inside the customer-service window (previously free there), and service messages are billed at the utility rate with the first 1,000 per phone number each month free. Pass service to include them; omit it to leave service out. Runs locally. This is Meta's platform fee only: a BSP/provider adds its own fee on top, so treat it as a floor, not a quote.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
marketYesRecipient market as a 2-letter code (e.g. "US", "IN", "BR", "GB", "DE"), or "ROW" for rest of world. Rates vary widely by market.
serviceNoMonthly count of service messages (free-form replies inside a customer-opened window). Optional. When given, the first 1,000 per phone number each month are free and the rest bill at the market's utility rate; omit to leave service out of the estimate.
utilityNoMonthly count of utility template messages (order updates, receipts, reminders).
marketingNoMonthly count of marketing template messages (promotions, offers).
authenticationNoMonthly count of authentication template messages (one-time passcodes).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / service
      Added value: +{
+  "description": "Monthly count of service messages (free-form replies inside a customer-opened window). Optional. When given, the first 1,000 per phone number each month are free and the rest bill at the market's utility rate; omit to leave service out of the estimate.",
+  "type": "number"
+}
  2. Changed1 schema field changed
    • removedInput schema / properties / utility_free_within_window_pct
      Removed value: -{
-  "description": "Percentage (0–100) of utility messages sent inside a free 24-hour customer-service window; these are not billed. Optional, default 0.",
-  "type": "number"
-}
  3. Changed1 schema field changed
    • changedInput schema / properties / market / enum
      Previous value: -[
-  "AR",
-  "BR",
-  "CL",
-  "CO",
-  "EG",
-  "FR",
-  "DE",
-  "HK",
-  "HU",
-  "IN",
-  "ID",
-  "IL",
-  "IT",
-  "MY",
-  "MX",
-  "NL",
-  "NG",
-  "PK",
-  "PE",
-  "PL",
-  "QA",
-  "RO",
-  "RU",
-  "SA",
-  "SG",
-  "ZA",
-  "ES",
-  "TR",
-  "AE",
-  "GB",
-  "NA",
-  "AFRICA",
-  "APAC",
-  "CEE",
-  "LATAM",
-  "MIDEAST",
-  "WEUROPE",
-  "OTHER"
-]New value: +[
+  "AR",
+  "BD",
+  "BR",
+  "CL",
+  "CO",
+  "EG",
+  "FR",
+  "DE",
+  "HK",
+  "HU",
+  "IN",
+  "ID",
+  "IQ",
+  "IL",
+  "IT",
+  "KZ",
+  "KW",
+  "MY",
+  "MX",
+  "MA",
+  "NP",
+  "NL",
+  "NG",
+  "OM",
+  "PK",
+  "PE",
+  "PL",
+  "QA",
+  "RO",
+  "RU",
+  "SA",
+  "SG",
+  "ZA",
+  "ES",
+  "LK",
+  "TR",
+  "UA",
+  "AE",
+  "GB",
+  "NA",
+  "AFRICA",
+  "APAC",
+  "CEE",
+  "LATAM",
+  "MIDEAST",
+  "WEUROPE",
+  "OTHER"
+]
  4. First observed

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries full burden and exceeds it: it discloses the billing changes ('As of 1 October 2026 utility is billed even inside the customer-service window'), the volume-tier discounts, the free tier for service messages, and the fact that the calculation runs locally. It also sets expectations about the output being a floor, not a quote. This is comprehensive behavioral disclosure for a local calculator.

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 description is a single dense paragraph, but every sentence earns its place: purpose, billing rules, parameter handling, execution, and a caveat. It is technically longer than ideal, yet not bloated—each clause adds necessary information. The front-loaded purpose makes it scannable despite its length.

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 calculator with five parameters and no output schema, the description adequately covers output ('itemized breakdown and total in USD'), parameter semantics, and edge cases (optional service, market variants). It doesn't describe the exact breakdown structure or rounding behavior, but that is minor given the tool's straightforward nature and the absence of an output schema requirement.

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?

Although schema coverage is 100%, the description adds meaningful context beyond the field descriptions: it clarifies that marketing is always billed, utility/authentication have tier discounts, and service messages follow a specific free-1000 rule. The 'market' parameter's locality is also contextualized in the billing rules. Structural schema already defines enums/labels, so the added value is the pricing logic, which is significant.

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 states a specific verb ('Estimate') and resource ('monthly WhatsApp Business (Cloud) API cost'), and clearly differentiates from siblings like get_whatsapp_rates and get_whatsapp_limits by focusing on cost estimation with billing rules and a USD total. It also mentions the specific pricing model (in effect since 1 July 2025), leaving no ambiguity about what the tool computes.

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?

The description explains the tool's scope ('Meta's platform fee only ... treat it as a floor, not a quote') and which parameters to include (e.g., 'Pass `service` to include them; omit it to leave service out'). It does not explicitly contrast against sibling tools, but the use case is evident from the stated purpose and the note about running locally. Minor gap: no explicit 'use this instead of get_whatsapp_rates for a full cost projection'.

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

All WhaTools — WhatsApp tools toolsInspect
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