Skip to main content
Glama
ReportProof MCP Server

ReportProof MCP Server

by vikyathhj-ui

compute_metrics

Calculates exact marketing totals, percentage changes, CTR, CPC, CPA, ROAS, goal progress, top movers, and anomalies from GA4, Google Ads, Meta Ads, or CSV/JSON data for report writing.

Instructions

Compute exact report metrics from marketing data: totals, % change vs previous period or last year, CTR, CPC, CPA, ROAS and rates recomputed from totals (never averaged), blended ad totals, goal progress, top movers and anomalies, with ready-to-print display strings. Use these numbers when writing a report.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "compute_metrics"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoCurrent period end, YYYY-MM-DD.
dataNoJSON sources: [{name, rows}] with plain row objects, [{name, ga4_report}] with a GA4 runReport response unchanged, or [{name, google_ads}] with a Google Ads search/searchStream response unchanged.
filesNoCSV exports: [{name, content}] (content = CSV text). Use content_base64 for UTF-16 files.
goalsNoTargets, e.g. {"conversions": 150, "cpa@blended": 40}.
startNoCurrent period start, YYYY-MM-DD. Omit to use the latest complete month.
compareNoCompare with the previous period (default) or the same period last year.
currencyNo3-letter currency code if the data doesn't say, e.g. USD or INR.
number_styleNoindian = lakh/crore grouping.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
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 meaningful work: it declares results are 'exact', that rates are recomputed from totals and 'never averaged', and that comparison can be vs previous period or last year, plus that output includes ready-to-print display strings. It does not state side effects, idempotency, or what happens with malformed input, which is the remaining gap.

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 verb and the metric inventory, then the usage instruction last where it belongs. The metric enumeration is long but each term is substantive; there is no filler or redundant restatement of the name.

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 an eight-parameter tool with nested objects and no output schema, the description is largely sufficient: it enumerates the returned metric families and mentions display strings, so an agent knows roughly what comes back. Remaining gaps are the mutual exclusivity/precedence of data vs files and any failure behavior, which the schema only partly covers.

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%, so all eight parameters are already documented in-schema, establishing a baseline of 3. The description adds only marginal meaning beyond that — the compare semantics ('vs previous period or last year') and the never-averaged recomputation rule — but adds nothing about data vs files interplay, goal key formats like 'cpa@blended', or currency handling.

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 (compute) and resource (report metrics) and enumerates the exact metric families produced — totals, % change, CTR/CPC/CPA/ROAS, blended totals, goal progress, top movers, anomalies. This is far more precise than a restatement of the name. It does not explicitly name or differentiate itself from check_report/verify_report, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The closing sentence 'Use these numbers when writing a report' implies the usage context but gives no when/when-not rules and never mentions the check_report or verify_report siblings. An agent must infer that this is the computation step and the siblings are validation steps.

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

Deploy Server

Other Tools