Skip to main content
Glama

Oran Analiz Bot

Oran analizi

analyze_odds
Read-only

Uygulamanın asıl analizi: seçilen oranlara (± tolerans) en yakın geçmiş maçları bulur; bu maçların nasıl bittiğini (her market için sonuç dağılımı: MS, İY, alt/üst, KG vb.), eşleşen maç sayısını ve en yakın maçları (maç, tarih, skor; satırlarda oran değeri yoktur) döner. Seçimler match_odds'tan market + sonuç çiftleridir (ör. 'Maç Sonucu' / '2'); birden çok seçim birlikte sağlanmalıdır. Oran verilmezse maçın kendi oranı kullanılır. provider ile analiz o büronun oranı ve oran geçmişiyle yapılır (varsayılan: kapanışta nesine, mode=opening ile iddaa açılış); büroda olmayan market reddedilir ve mevcut marketler listelenir. Kapsam (filter: aynı lig/ülke/takımlar/H2H/hakem, gün, saat, skor), zaman aralığı, tolerans, sıralama ve sayfa uygulamadaki seçeneklerin aynısıdır; savedFilter ile kayıtlı filtre adıyla uygulanır. Geçmiş bir maçta havuz maçın başlama saatiyle sınırlıdır. Kullanıcının günlük analiz hakkından düşer. Eşleşme yoksa çıktıda not vardır.

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": {
      "matchKey": "<matchKey>"
    },
    "name": "analyze_odds"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoMaç listesinin sayfası (sayfa başına 20). İstatistikler ilk sayfada tüm eşleşmeler üzerindendir.
filterNoGeçmiş maçların kapsamı (uygulamadaki gibi). Verilmezse tüm maçlar.
matchKeyYeslist_matches'ten alınan matchKey.
providerNoİsteğe bağlı büro providerKey (match_odds `bureaus`, ör. pinnacle, bet365). Analiz o büronun oranı ve oran geçmişiyle yapılır; oran her zaman büronun kendi kapanış (mode=opening ile açılış) oranıdır. Varsayılan: kapanışta nesine, açılışta iddaa. Büronun vermediği market reddedilir.
sortModeNoDönen maçların sırası (varsayılan: odds_nearest, en yakın oran).
timeRangeNoZaman aralığı: last_1_week | last_2_weeks | last_1_month | last_3_months | all_time (varsayılan) | last_N_days (ör. last_400_days) | between_YYYY-MM-DD_YYYY-MM-DD.
toleranceNoOran toleransı (oranın ± etrafı, ör. 0.05). Varsayılan: kullanıcının uygulamadaki ayarı.
selectionsNo
savedFilterNoSeçimler yerine kullanıcının kayıtlı filtrelerinden birini ADIYLA (list_saved_filters'taki ad) bu maça uygular. Burada ayrıca verilmedikçe filtrenin kapsamı, zamanı ve toleransı kullanılır.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real behavioral context beyond that — quota consumption, the pool being capped at the match's kickoff time, bureau-unsupported markets being rejected with the available markets listed, and a note in the output when nothing matches. Missing on its own but present in the schema are provider/mode defaults; the description does restate them, which is minor redundancy rather than contradiction.

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 core purpose and return shape before branching into provider, filter, savedFilter, and edge cases. Dense but almost every clause carries new information; minor overlap with the schema on defaults and tolerance keeps it from a 5.

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?

With 9 parameters, nested filter/savedFilter, no output schema, and a quota-consuming read operation, the description covers what an agent needs: inputs sourced from match_odds, default behavior, bureau rejection path, pool limitation for past matches, result shape, and the empty-match note. Return values are explained as fully as possible given no output schema exists.

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 89%, so baseline would be 3, but the description adds cross-tool meaning the schema cannot: selections are pairs sourced from match_odds, multiple selections must be combined, tolerance is a ± band around the odd, and savedFilter inherits scope/time/tolerance unless overridden. provider semantics (analysis uses that bureau's odds and history, defaults per mode, unsupported market rejected) go beyond the schema's field description.

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 verb and resource: it finds past matches whose odds are nearest the selected odds within a tolerance and returns their outcome distribution. Very concrete, including what the returned rows contain and do not contain (no odds values in rows). It never explicitly names a sibling it is not (e.g. similar_matches, find_fixtures_by_odds), so sibling differentiation relies on the implicit phrase 'the app's main analysis'.

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?

Gives usable context: selections must be market+outcome pairs taken from match_odds and supplied together, a hypothetical odd may be given (iddaa only) or the match's own odd is used, and savedFilter can replace explicit selections by name. It also warns that the call consumes the user's daily analysis quota, which materially affects when an agent should invoke it. No explicit when-not or sibling comparison is provided.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources