Skip to main content
Glama

saas_metrics

Read-onlyIdempotent

SaaS health advisor. POST your MRR/customers (+ optional churn/CAC/margin/growth) and get ARR/ARPA/LTV/CAC/payback/Rule-of-40/NRR/GRR computed, each with a health tag, plus an overall grade + a ranked "what to fix first" focus list. Deterministic math + advisory, no LLM.

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": {
      "mrr": "<mrr>",
      "customers": "<customers>"
    },
    "name": "saas_metrics"
  }
}

Input Schema

NameRequiredDescriptionDefault
cacNoAcquisition cost per customer. Wins over sales_marketing_spend / new_customers.
mrrYesCurrent monthly recurring revenue.
cogsNoPeriod cost of goods sold.
new_mrrNoMRR from new customers. Accepted and validated, but no current metric uses it.
revenueNoPeriod revenue; with cogs, derives gross margin.
customersYesCurrent paying accounts; divisor for ARPA.
prior_mrrNoMRR one period earlier. Enables growth, NRR and GRR; wins over growth_pct.
growth_pctNoMRR growth in percent, used only when prior_mrr is absent.
churned_mrrNoMRR lost to cancellations. Drives churn rate, LTV, NRR and GRR.
expansion_mrrNoMRR gained from upgrades. Feeds NRR.
new_customersNoCustomers acquired this period.
contraction_mrrNoMRR lost to downgrades. Feeds NRR and GRR.
gross_margin_pctNoGross margin in percent, e.g. 78. Wins over revenue/cogs.
sales_marketing_spendNoSales + marketing spend; with new_customers, derives CAC.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed16 schema fields changed
    • addedInput schema / properties / cac / description
      Added value: +"Acquisition cost per customer. Wins over sales_marketing_spend / new_customers."
    • addedInput schema / properties / churned_mrr / description
      Added value: +"MRR lost to cancellations. Drives churn rate, LTV, NRR and GRR."
    • addedInput schema / properties / cogs
      Added value: +{
      +  "description": "Period cost of goods sold.",
      +  "type": "number"
      +}
    • addedInput schema / properties / contraction_mrr
      Added value: +{
      +  "description": "MRR lost to downgrades. Feeds NRR and GRR.",
      +  "type": "number"
      +}
    • addedInput schema / properties / customers / description
      Added value: +"Current paying accounts; divisor for ARPA."
    • addedInput schema / properties / customers / exclusiveMinimum
      Added value: +0
    • addedInput schema / properties / expansion_mrr / description
      Added value: +"MRR gained from upgrades. Feeds NRR."
    • addedInput schema / properties / gross_margin_pct / description
      Added value: +"Gross margin in percent, e.g. 78. Wins over revenue/cogs."
    • addedInput schema / properties / growth_pct
      Added value: +{
      +  "description": "MRR growth in percent, used only when prior_mrr is absent.",
      +  "type": "number"
      +}
    • addedInput schema / properties / mrr / description
      Added value: +"Current monthly recurring revenue."
    • addedInput schema / properties / mrr / minimum
      Added value: +0
    • addedInput schema / properties / new_customers / description
      Added value: +"Customers acquired this period."
    • addedInput schema / properties / new_mrr / description
      Added value: +"MRR from new customers. Accepted and validated, but no current metric uses it."
    • addedInput schema / properties / prior_mrr / description
      Added value: +"MRR one period earlier. Enables growth, NRR and GRR; wins over growth_pct."
    • addedInput schema / properties / revenue
      Added value: +{
      +  "description": "Period revenue; with cogs, derives gross margin.",
      +  "type": "number"
      +}
    • addedInput schema / properties / sales_marketing_spend / description
      Added value: +"Sales + marketing spend; with new_customers, derives CAC."
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so safety is covered. The description adds genuinely new context beyond them: the math is deterministic with no LLM involvement, and the response includes per-metric health tags, an overall grade, and a ranked 'what to fix first' list.

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?

Two dense sentences, front-loaded with the verb and required inputs, then outputs, then the determinism caveat. Every clause carries information; no filler or repetition of the title.

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 14 parameters and no output schema, the description does the necessary work by enumerating the returned metrics and the advisory artifacts, which lets an agent set expectations without a schema. Minor gaps remain around partial-data behavior (what happens when prior_mrr is missing) and edge cases such as negative or zero values.

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 the schema itself already documents each parameter's role and precedence (e.g. cac 'Wins over sales_marketing_spend / new_customers'). The description adds only the high-level split of required vs optional groups and the metric families they unlock, without unit/format detail beyond 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?

Names a specific operation and domain: compute SaaS health metrics from MRR/customer inputs into ARR/ARPA/LTV/CAC/payback/Rule-of-40/NRR/GRR, plus grade and a ranked focus list, with 'Deterministic math + advisory, no LLM' clarifying the mechanism. It is unmistakable against siblings like rate_call, sprint_health, or estimate_sanity.

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?

Tells the agent the minimum viable input set (mrr and customers) and that churn/CAC/margin/growth are optional add-ons, which is clear invocation context. It stops short of explicit when-not-to-use conditions or naming an alternative for cases the tool cannot cover.

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.