Skip to main content
Glama

calculate_support_tco

Read-onlyIdempotent

Compares per-resolution AI support pricing from Intercom, Gorgias, and Zendesk against flat-rate and metered plans to calculate monthly and annual TCO, effective cost per ticket, and recommended plan offline.

Instructions

Deterministic total-cost-of-ownership (TCO) and unit-economics calculator comparing per-resolution AI support pricing (Intercom Fin at $0.99/resolution + seats, Gorgias AI automated interaction pricing, Zendesk AI) against flat-rate OctaDezx tiers (Starter $29/mo, Pro $99/mo, Advanced $199/mo) and Enterprise metered billing ($499/mo minimum). Runs completely offline with no API key, returning recommendedPlan, monthlyUsd, annualUsd, effectiveCostPerTicketUsd, and competitor savings.

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": {
      "monthlyTickets": "<monthlyTickets>"
    },
    "name": "calculate_support_tco"
  }
}

Input Schema

NameRequiredDescriptionDefault
teamSeatsNoNumber of human support team seats required (default 3).
monthlyTicketsYesTotal monthly customer support tickets or inquiries across all messaging channels.
zendeskSeatUsdNoZendesk Suite monthly price per agent seat in USD (default 55).
intercomSeatUsdNoIntercom monthly price per agent seat in USD (default 29).
aiResolutionRateNoExpected fraction of monthlyTickets resolved autonomously by AI (from 0.0 to 1.0, default 0.65).
monthlyVoiceMinutesNoExpected monthly inbound/outbound AI phone voice minutes (default 0).
avgMessagesPerTicketNoAverage AI messages exchanged per customer ticket (default 4).
gorgiasBaseMonthlyUsdNoGorgias base monthly helpdesk subscription in USD (default 60).
gorgiasPerAutomatedUsdNoGorgias AI fee per automated ticket resolution in USD (default 0.95).
intercomPerResolutionUsdNoIntercom Fin fee per resolved conversation in USD (default 0.99).
zendeskAutomatedResolutionUsdNoZendesk AI add-on fee per automated resolution in USD (default 1.50).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral facts: deterministic output, fully offline operation with no API key or external calls, and the specific returned fields (recommendedPlan, monthlyUsd, annualUsd, effectiveCostPerTicketUsd, competitor savings). It does not flag that results are model estimates dependent on aiResolutionRate assumptions, which keeps it from a 5.

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?

Two sentences, front-loaded with the tool's identity before the return-value list, with no filler. The vendor-pricing parenthetical is dense but each element carries pricing information the agent would otherwise have to guess.

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?

With no output schema, the description takes on the burden of describing returns and does so by naming the five key fields including competitor savings. Combined with a fully documented 11-parameter schema and read-only annotations, an agent has enough to call this correctly; only the assumption-sensitivity of the output is left implicit.

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 description coverage is 100% across all 11 parameters, each with defaults and bounds documented, so the baseline is 3. The description restates some pricing constants that mirror schema defaults ($0.99/resolution, $29/mo, $499/mo minimum) but adds no interpretation of how parameters interact, such as how aiResolutionRate and monthlyTickets combine to drive effectiveCostPerTicketUsd.

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 — a deterministic TCO and unit-economics calculator — and names exactly what it compares: per-resolution AI support pricing (Intercom Fin $0.99/resolution + seats, Gorgias automated-interaction pricing, Zendesk AI) against OctaDezx flat tiers and Enterprise metered billing. No sibling tool (audit_knowledge_base, verify_order, send_customer_reply, etc.) overlaps with a pricing calculator, so the agent can route unambiguously.

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 comparison framing makes the use case clear — cost/plan evaluation when a customer weighs AI support vendors — and the 'no API key, runs completely offline' note signals it is safe to call freely. It stops short of explicit trigger phrasing ('use when the user asks about pricing') or stated exclusions, so it is clear context rather than full when/when-not guidance.

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