Skip to main content
Glama
TurkActuary MCP

TurkActuary MCP

by afsharid

bornhuetter_ferguson

Read-onlyIdempotent

Estimates outstanding claims reserves from cumulative loss triangles, earned premiums, and expected loss ratios, with optional tail factor; supports paid and incurred bases.

Instructions

Kazanılmış prim ve a-priori hasar oranlarıyla BF tahmini. tail_factor isteğe bağlıdır; kullanıcı vermediyse gönderme (varsayılan 1, en az 1). Sonucun adını reserve_interpretation alanından al: paid bazında toplam ödenmemiş rezervdir, IBNR diye adlandırma.

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": {
      "triangle": "<triangle>",
      "basis": "<basis>",
      "earned_premiums": "<earned_premiums>",
      "expected_loss_ratios": "<expected_loss_ratios>"
    },
    "name": "bornhuetter_ferguson"
  }
}

Input Schema

NameRequiredDescriptionDefault
basisYes
triangleYesKümülatif üçgen; artımlı veri değildir.
tail_factorNoSonlu ondalık; oranlar yüzde değil (0.10 = %10).
earned_premiumsYes
expected_loss_ratiosYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare this is a safe, idempotent, closed-world read, so the description is not obliged to restate that. It adds real behavioral context beyond them: the default and minimum for tail_factor, and an explicit instruction not to relabel the paid-basis output as IBNR, which prevents a downstream reporting error.

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?

Three short sentences, each carrying distinct information: what the tool computes, how to handle the optional parameter, and how to name the output. The optional-parameter rule and the output-naming warning are front-loaded with no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool takes five parameters with four required and has no output schema, so the description carries substantial weight. It covers tail_factor handling and the meaning of the paid-basis result, but leaves the incurred basis uninterpreted and says nothing about how earned_premiums and expected_loss_ratios must align with the triangle rows, which is a realistic source of invocation error.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 40%, so the description must compensate, and it does for the weakest parameter: it supplies the default value (1) and lower bound (minimum 1) for tail_factor, which the schema does not state. It also pins down how to interpret the result with respect to the basis parameter, adding meaning the enum alone cannot convey.

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?

The description names a specific method and its inputs: a Bornhuetter-Ferguson estimate driven by earned premium and a-priori loss ratios. An agent can tell it is a reserving/estimation tool rather than a utility, though it does not explicitly contrast itself with the sibling chain_ladder method that a user might also reach for.

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?

It gives concrete operational guidance for one input ('tail_factor is optional; if the user didn't supply it, don't send it') and instruction on how to label the result, which is genuinely useful. It does not state when to prefer BF over alternative reserving methods or what preconditions the triangle and premium arrays must satisfy relative to each other.

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