Skip to main content
Glama
zirve-finansman-mcp

zirve-finansman-mcp

by yibudak

yevmiye_ara

Read-only

Search journal lines by document number, tax ID, description, account prefix, amount, or date range to locate external system records in Zirve.

Instructions

Yevmiye satırlarında arama yapar; dış sistem kayıtlarını Zirve'de bulmak için ana araçtır.

evrak_no: fatura/belge numarasında geçen metin. vergi_no: satırdaki VKN/TCKN (tam eşleşme). aciklama: satır açıklamasında geçen metin (büyük-küçük harf ve Türkçe karakter ayrımı gözetmez). hesap_on_eki: hesap kodu başlangıcı (ör. "120", "600"). tutar_min/tutar_max: satırın TL tutarı (borç veya alacak); tam tutar için ikisine aynı değeri verin. baslangic/bitis: fiş tarihi aralığı. En az bir filtre verin.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "yevmiye_ara"
  }
}

Input Schema

NameRequiredDescriptionDefault
yilNo
bitisNo
firmaNo
limitNo
offsetNo
aciklamaNo
evrak_noNo
vergi_noNo
baslangicNo
tutar_maxNo
tutar_minNo
hesap_on_ekiNo

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 declare readOnlyHint=true, so the safety profile is covered. The description adds genuinely useful behavior beyond that: aciklama matching ignores case and Turkish character differences, vergi_no requires exact match, amounts may be debit or credit, and at least one filter must be supplied. It omits any statement about result volume or pagination behavior despite limit/offset existing.

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?

The purpose is front-loaded in one sentence and the rest is a tight parameter glossary where each line earns its place. No filler or repetition, though the missing parameters mean the structure is efficient but not exhaustive.

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

Completeness5/5

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

For a 12-parameter read-only search tool with no output schema, the definition covers the intent, the mandatory-filter rule, and the matching semantics an agent needs to construct a valid query. The unexplained firma/yil/limit/offset are the main residual gap, but their names are largely self-evident and the core search contract is complete.

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 coverage is 0%, so the description carries the full explanatory burden, and it does define seven parameters with real semantics (prefix matching for hesap_on_eki, exact-match for vergi_no, equal min/max for an exact amount). However, four parameters — firma, yil, limit, offset — receive no explanation at all, and firma is a critical scoping input in a multi-company ledger.

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 first sentence gives a specific verb and resource (searching yevmiye/journal lines) and positions the tool as the primary way to locate external-system records in Zirve, which implicitly separates it from voucher-level siblings. It stops short of naming a concrete alternative, so an agent must still guess against fis_getir/fisleri_listele.

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?

The closing constraint 'En az bir filtre verin' plus the 'ana araçtır' framing implies when to reach for this tool, and the filter semantics hint at narrowing strategies. But there is no explicit when-not guidance and no named alternative for voucher-level retrieval, leaving routing to inference.

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