Skip to main content
Glama

GameGene: 定石 (recurring design judgements)

gamegene_joseki
Read-only

Design rules of thumb, and games that broke them: fresh angles for any genre. 設計の定石と、それを意図的に外した作品 (departure) を返す。«なぜこう作るか» のほか、ジャンルの前提を崩して新しさを出したいときの切り口探しに使う。Recurring game design judgements seen across many games (for example: reduce output randomness, never let a loss feel unfair, respect the player's time), each with who said it first and example games with the makers' own words. Use it when someone asks why games are designed a certain way, or weighs a design choice such as luck, fairness, difficulty, risk and reward, or how much information to show the player. Its cases can include games that deliberately broke the judgement (departure), which helps when looking for a fresh angle on a genre. 定石 (作品をまたいで繰り返し現れる設計の判断。例 «出力の運を減らす» «理不尽に負けさせない») を返す。gene が «具体の仕組み» なら、定石は «仕組みを選ぶ理由» で、1つの定石が複数の gene をまたぐ。原則ではなく局面しだいの判断として記録している。slug を渡すと1件の全部: 言っていること、出所 (origins — 誰が・どこで・いつ言ったか。kind は coined 言い出した / earlier それより前にあった / popularized 広めた / restated 言い直した、出典つき)、事例 (cases — 作り手の発言である主張への結び。relation は names 定石の語・考えを名指した / same_judgment 名指さずに同じ判断を語った / departure 定石外し・限界)、隣の定石 (links)、またぐ gene (geneSlugs)。slug を省くと一覧 (名前と言っていることと事例の数)。無い slug は null。Without slug it is the light list of every joseki's slug: call it once to find the slug, then read one; when the slug is already known (for example from a design playbook), call it directly without searching. same_judgment は GameGene が当てはめたもので、作り手がその定石を名指したわけではない — 答えるときは names と分けて言うこと。事例の主張の全文と根拠は gamegene_claims で読む。

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": "gamegene_joseki"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly/openWorld=false, but the description adds what they cannot: no slug yields a light list (name, claim, case count), a missing slug yields null, and a slug yields the full record with origins, cases, links and geneSlugs. It also discloses an important interpretive caveat — same_judgment is GameGene's own attribution, not the maker naming the judgement, and must be reported separately from names.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and behavior are front-loaded and the data model taxonomy (coined/earlier/popularized/restated; names/same_judgment/departure) is genuinely useful. But the Japanese and English halves substantially duplicate each other, so a large fraction of the text is repetition rather than added information.

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 single-optional-param read tool with no output schema, the description supplies the return shape, the enum-like relation semantics, the null case, the cross-tool handoff for full claim text, and the attribution caveat. Nothing needed to call or interpret it correctly is missing.

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 0%, so the description must carry the whole burden and largely does: it explains both modes (omit slug = list, provide slug = single full record), and the null behavior for an unknown slug. It stops short of giving slug format or examples, leaving an agent to guess the naming convention.

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 resource and verb: returns recurring game design judgements (定石) with origins and example cases, and explicitly contrasts itself with the sibling concept gene ('gene が «具体の仕組み» なら、定石は «仕組みを選ぶ理由»'). An agent can distinguish this from gamegene_genes and gamegene_claims without opening any schema.

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

Usage Guidelines5/5

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

Gives concrete when-to-use triggers ('when someone asks why games are designed a certain way, or weighs a design choice such as luck, fairness, difficulty, risk and reward') and a procedural rule: call once without a slug to get the list, then read one by slug; skip the search entirely if the slug is already known from a playbook. It also routes deeper reading to gamegene_claims, naming the alternative explicitly.

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