Skip to main content
Glama
TurkActuary MCP

TurkActuary MCP

by afsharid

credibility_estimate

Read-onlyIdempotent

Computes a Bühlmann credibility estimate by blending observed and prior means using exposure units and a supplied k value.

Instructions

Bühlmann tipi güvenilirlik ağırlığı (k açıkça verilir).

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": {
      "observed_mean": "<observed_mean>",
      "exposure_units": "<exposure_units>",
      "prior_mean": "<prior_mean>",
      "k": "<k>"
    },
    "name": "credibility_estimate"
  }
}

Input Schema

NameRequiredDescriptionDefault
kYesSonlu ondalık; oranlar yüzde değil (0.10 = %10).
prior_meanYesSonlu ondalık; oranlar yüzde değil (0.10 = %10).
observed_meanYesSonlu ondalık; oranlar yüzde değil (0.10 = %10).
exposure_unitsYesSonlu ondalık; oranlar yüzde değil (0.10 = %10).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
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 fully covered by structured data. The description adds one behavioral fact beyond that: k is an explicitly supplied input rather than something derived. It discloses nothing about determinism of the output or its scale.

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 compact sentence with the key computation front-loaded and no filler. Its brevity is efficient, though it borders on under-specification rather than optimal economy.

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 four-parameter required-input math tool with full schema coverage and no output schema, most calling details are already structured. The missing piece is what quantity comes back (the weight itself or a blended estimate), which the description leaves to inference.

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 all four parameters are already documented, including the finite-decimal and ratio-not-percentage convention. The description only reinforces that k is a caller-provided value, which is marginal added meaning over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific computation ("Bühlmann tipi güvenilirlik ağırlığı") and adds a qualifier that k is supplied explicitly rather than estimated. However, it never states what is actually returned (the credibility weight Z versus a credibility-weighted mean), despite the tool being named credibility_estimate, and it draws no boundary against actuarial siblings such as chain_ladder or bornhuetter_ferguson.

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 when-to-use guidance, no prerequisite context, and no named alternative. The parenthetical "k açıkça verilir" hints at a variant where k comes from data, but it does not say which sibling or condition that would select.

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