Skip to main content
Glama

financial_trend_anomaly

Read-onlyIdempotent

[Deterministic forensic accounting analysis. Pure calculation, read-only, side-effect free]. Evaluates multi-period financial statements across 2+ fiscal years: CAGR revenue and EBITDA growth, profitability margins (ROE, ROI, ROS, EBITDA margin), Beneish M-Score for earnings manipulation detection, and Benford Law first-digit distribution tests against sector ATECO/NACE benchmarks. Usage: Use this tool to detect aggressive revenue recognition, accounting anomalies, or fraudulent manipulation in historical financial statements. Do NOT use for bankruptcy prediction (use 'corporate_default_predictor') or intrinsic enterprise valuation (use 'dcf_wacc_valuation'). Returns: JSON object with { beneishMScore: number, earningsManipulationRisk: 'LOW' | 'MEDIUM' | 'HIGH', benfordAnomalyDetected: boolean, cagrRevenue: number, marginTrends: object, forensicFlags: string[] }.

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": {
      "periods": "<periods>"
    },
    "name": "financial_trend_anomaly"
  }
}

Input Schema

NameRequiredDescriptionDefault
periodsYesAt least 2 chronological balance sheet periods for trend analysis
atecoNaceCodeNoSector ATECO/NACE code (e.g. J.62.01, C.25) for industry benchmarks

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description reinforces this with 'deterministic, pure calculation, read-only, side-effect free', plus it discloses the minimum data window (2+ fiscal years) and the exact return keys including risk enums. It does not state what happens when optional Beneish inputs (receivables, COGS, SG&A, debt) are omitted, which is the one behavioral question an agent still faces, so it stops short of 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?

It is front-loaded with a bracketed behavior tag, then Usage, then Returns, so an agent scans it in one pass. The bracketed clause largely restates the annotations and is the one segment that does not fully earn its place, but the rest is tight and well-sectioned.

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 computational tool with no output schema, the description supplies the return object shape and field names, which is the critical missing piece. It leaves the interpretation of forensicFlags and the scoring thresholds of the M-Score unstated, so it is strong but not exhaustive.

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%, so both the periods array and atecoNaceCode role are already documented, including which fields feed which Beneish index. The description adds only the '2+ fiscal years' scope and the benchmark framing for the sector code, which the schema essentially states too; baseline 3 is appropriate.

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 ('Evaluates multi-period financial statements') and enumerates exactly what is computed: CAGR revenue/EBITDA growth, ROE/ROI/ROS/EBITDA margins, Beneish M-Score, and Benford first-digit tests. It also names the two adjacent tools it is not, so an agent can separate it from valuation and default prediction without opening any schema.

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

Usage Guidelines5/5

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

Gives an explicit positive use case ('detect aggressive revenue recognition, accounting anomalies, or fraudulent manipulation in historical financial statements') and explicit exclusions with named alternatives ('Do NOT use for bankruptcy prediction (use corporate_default_predictor) or intrinsic enterprise valuation (use dcf_wacc_valuation)'). Nothing is left to inference about routing.

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