Skip to main content
Glama
TurkActuary MCP

TurkActuary MCP

by afsharid

combined_ratio

Read-onlyIdempotent

Calculates incurred loss, LAE, expense, and combined ratios on the same earned-premium basis using losses, adjustment expenses, acquisition costs, other expenses, and earned premium.

Instructions

Aynı kazanılmış esasta hasar (LAE dahil), gider ve bileşik oran.

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": {
      "incurred_losses": "<incurred_losses>",
      "loss_adjustment_expenses": "<loss_adjustment_expenses>",
      "acquisition_costs": "<acquisition_costs>",
      "other_expenses": "<other_expenses>",
      "earned_premium": "<earned_premium>"
    },
    "name": "combined_ratio"
  }
}

Input Schema

NameRequiredDescriptionDefault
earned_premiumYesSonlu ondalık; oranlar yüzde değil (0.10 = %10).
other_expensesYesSonlu ondalık; oranlar yüzde değil (0.10 = %10).
incurred_lossesYesSonlu ondalık; oranlar yüzde değil (0.10 = %10).
acquisition_costsYesSonlu ondalık; oranlar yüzde değil (0.10 = %10).
loss_adjustment_expensesYesSonlu ondalık; oranlar yüzde değil (0.10 = %10).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine domain context — that LAE is folded into the loss component and that all inputs must share the same earned basis — but it never states what the response contains (loss ratio, expense ratio, and combined ratio separately, or one number), which matters because there is no output schema.

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?

A single dense sentence with no filler, and the key qualifier (same earned basis) is front-loaded. It is terse to the point of omitting the return shape, but nothing is redundant or padded.

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?

For a five-required-parameter calculator with no output schema, the definition explains the input convention and component treatment adequately. It falls short on what the call returns and on any error behavior for mixed bases, which an agent would want before invoking it.

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% and every parameter is documented as a finite decimal with a percentage convention, so the schema does the heavy lifting. The description contributes only the interpretive rule that LAE belongs in the loss component and that all inputs are on an earned basis; baseline 3 is appropriate.

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 actuarial metric — the combined ratio — and specifies its construction: loss (including LAE), expense, and the combined figure on the same earned basis. An agent can identify it as a ratio calculator rather than a generic statistics tool, though it does not distinguish itself from sibling tools like portfolio_metrics or chain_ladder.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus alternatives such as portfolio_metrics, nor any prerequisites or exclusions. The agent must infer from the name and one-line formula that this is the right choice for combined-ratio computation.

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