Skip to main content
Glama
TurkActuary MCP

TurkActuary MCP

by afsharid

mevzuat_ara

Read-onlyIdempotent

Search Turkish insurance legislation, selected Yargıtay compensation decisions, and explanatory notes by query or date; returns source, covered article numbers, and text for citation-ready answers.

Instructions

Türkiye sigortacılık mevzuatı (5684 sayılı Kanun, yönetmelikler, tebliğler; konsolide, erişim 2026-10-18), seçilmiş Yargıtay tazminat kararları (destekten yoksun kalma, iş göremezlik; künyeli) ve öğretici notlarda arama (embedding sunucusu varsa BM25 + anlamsal karma v5, yoksa BM25 v2). Parça kimliği, başlık, kaynak, kapsanan madde numaraları (maddeler) ve metin döner. Atıfta madde numarasını yalnız 'maddeler' alanından al; tahmin etme.

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": {
      "sorgu": "<sorgu>"
    },
    "name": "mevzuat_ara"
  }
}

Input Schema

NameRequiredDescriptionDefault
adetNoParça sayısı (varsayılan 4).
sorguYesTürkçe arama sorgusu ya da soru.
tarihNoYYYY-MM-DD; o tarihte geçerli parçalar.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is real: it discloses that retrieval is BM25 + semantic hybrid v5 when an embedding server is present and falls back to BM25 v2 otherwise, and that the corpus is a consolidated snapshot with an access date. It also names the returned fields, which the annotations cannot convey. It stops short of describing ranking, result limits, or behavior on empty queries.

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?

Front-loaded with the corpus scope, then retrieval mechanics, then return fields, then the citation caveat — a sensible order. It is dense with stacked parentheticals ('5684 sayılı Kanun, yönetmelikler, tebliğler; konsolide, erişim 2026-10-18'), but nearly every clause carries operational information.

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 correctly compensates by naming the returned fields (chunk id, title, source, article numbers, text) and warns about the most likely agent error, fabricating article numbers. For a 3-parameter retrieval tool this is close to complete; only ranking/limit behavior and behavior on no-match remain unstated.

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 'sorgu', 'adet' (default 4, 1-10) and 'tarih' (YYYY-MM-DD, in-force date) are already documented in the schema. The description's mention of returning 'parça' (chunks) gives the agent useful framing for what 'adet' counts, but adds no syntax or format detail beyond the schema. Baseline 3 applies.

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 (arama/search) over a precisely scoped corpus: Turkish insurance legislation (Law 5684, regulations, communiqués), selected Yargıtay compensation decisions, and instructional notes. The scope is narrow enough that an agent can tell this apart from the actuarial siblings (chain_ladder, destekten_yoksun_kalma, etc.), which compute rather than retrieve.

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

Usage Guidelines4/5

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

The domain scoping implicitly tells the agent when to reach for this tool (legal/article lookup, citation grounding) and adds a concrete usage rule: take article numbers only from the 'maddeler' field, never guess. What is missing is explicit routing against alternatives (e.g., when to use belge_getir instead, or how this differs from the destekten_yoksun_kalma sibling for case law).

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