Skip to main content
Glama
TurkActuary MCP

TurkActuary MCP

by afsharid

chain_ladder

Read-onlyIdempotent

Calculates cumulative paid or incurred reserves from cumulative triangles, applies an optional tail factor, and returns unpaid reserve results—not pure IBNR—for actuarial reserving.

Instructions

Açık paid/incurred bazında kümülatif Chain Ladder; saf IBNR varsayılmaz. 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>"
    },
    "name": "chain_ladder"
  }
}

Input Schema

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

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (read-only, idempotent, non-destructive, closed-world), and the description adds real behavioral context: no pure IBNR assumption, tail_factor defaulting/minimum coercion, and how to interpret the output. It does not describe units, rounding, or error behavior when the triangle is malformed, which keeps it below 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?

Three short clauses, front-loaded with the method and basis, then the optional-parameter rule, then the output-naming rule. Dense but every clause carries actionable information; only the repeated IBNR caveat appears twice.

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 compensates by naming a result field (reserve_interpretation) and prescribing how the paid-basis total should be labeled. For a 3-parameter, closed-world calculation tool this is nearly sufficient; the maxItems=100 triangle bound and failure modes are left to the schema.

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

Parameters4/5

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

Schema coverage is 67%, and the description meaningfully supplements it for tail_factor by stating the omission default and the >=1 floor, which the schema does not. It repeats the cumulative (not incremental) nature of triangle and the paid/incurred basis already documented in the schema rather than adding to them.

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 method and scope: cumulative Chain Ladder on an explicit paid/incurred basis, and rules out the pure-IBNR assumption. An agent can distinguish it from bornhuetter_ferguson only by inference from the IBNR remark, since no sibling is named, so it falls 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?

Gives concrete operational guidance for tail_factor ('if the user didn't provide it, don't send it', default 1, minimum 1) and a naming rule for the result. It never states when to prefer this over reserve alternatives such as bornhuetter_ferguson, so usage guidance is implied rather than explicit.

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