Skip to main content
Glama

GameGene: 語で探す (search design records)

gamegene_search
Read-only

Game-design help (ideas, novelty): real games' sourced choices, makers' words. ゲーム制作の相談 (アイデア出し・新規性・差別化・行き詰まり) に、実在作の工夫と型を外した作品を、出典と作り手の言葉つきで返す (インディー作品を含む)。新しさの材料は、ジャンルに既に在るものと、その型を外した作品を知ることである。Sourced records beyond general knowledge: the makers' own words on what they aimed for and dropped, design lineages, and indie games. Searches GameGene's records of game design history: games, design genes (mechanics), people, claims (design decisions with the makers' intent and sources), trivia and joseki (recurring design judgements). Use it when someone making a game asks for precedents or references for a mechanic or system (for example a roguelite's meta progression or a deckbuilder's card rewards), or asks where a mechanic came from or which game did it first. More broadly, use it whenever someone making a game is unsure or stuck on a design question (balance, difficulty, rewards, pacing, how it feels, new ideas, standing out in a crowded genre) and real games could inform the answer. Most records are in Japanese: if an English term finds nothing, retry with the Japanese design word. 語 (題・別名・人名・gene 名・本文の一部) で、作品・gene・人物・主張・トリビア・定石を探す。ゲームを作る人の先例探しのほか、設計で迷っている・詰まっているとき全般 (釣り合い・難しさ・報酬・アイデア出し・新規性や差別化) に、ジャンルに既に在る工夫と型から外れた作品を引くのに使う。部分一致で、作品は最大60件・工夫 (claims) と定石は最大40件・ほかは最大20件 (作品を切ったときは gamesTotal と gamesNote、工夫を切ったときは claimsMore が付く)。語がジャンルやタグ (サバイバーズ系・ホラーなど) に当たると、その作品も games に入る。**slug が分からないときは、作品を全件引く前にこれを使う。**types (games / genes / people / claims / trivia / joseki) で探す種類を絞れる — slug を知りたいだけなら types: ["games"] にすると応答がずっと小さい。主張とトリビアは本文の先頭だけを返す (cut が true なら続きが在る) — 全文は gamegene_claims / gamegene_game で読む。日本語の本文を持つので、«映画» «漫画» のような語で本文を探すのにも使える。spoiler が true のトリビアはネタバレを含む — 読者が望むまで中身を伏せて伝えること。

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": {
      "query": "<query>"
    },
    "name": "gamegene_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYes
typesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover only the safety profile (readOnly, non-destructive, closed-world), and the description adds substantial behavior beyond that: partial matching, per-type result caps (60 games / 40 claims+joseki / 20 others), truncation markers (gamesTotal, gamesNote, claimsMore, cut), genre/tag hits being folded into games, and a spoiler flag on trivia with a caution about revealing it. It also discloses that most records are Japanese and advises retrying with a Japanese design term, which is critical operational context.

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?

The operational content is front-loaded reasonably well, but the description is very long and much of it is duplicated between the Japanese and English passages, with the 'when to use' guidance restated twice. Sentences themselves are informational, but the bilingual redundancy and repeated framing cost it efficiency.

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 two-parameter search tool with no output schema, the definition covers everything an agent needs: what is searched, result limits and truncation signals, how to narrow by type, how to escalate to detail tools, language pitfalls, and spoiler handling. Nothing material is left to inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

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 burden and largely does: it explains that `query` is a partial match against titles, aliases, person names, gene names, and body text, and even that body-text search can find words like «映画»/«漫画». It also enumerates the six `types` values and their effect on response size, compensating for the enum not being described in the schema (only the 200-char limit is left unstated).

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 and resource: it searches GameGene's records of game design history, enumerating the record kinds (games, genes, people, claims, trivia, joseki). It also distinguishes itself from siblings by naming gamegene_claims and gamegene_game as the place to read full text, so an agent can tell which tool to open.

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?

Explicit usage conditions are given: precedents for a mechanic/system, where a mechanic came from, and broader 'stuck on a design question' cases. It names alternatives for follow-up (gamegene_claims / gamegene_game for full text) and states a concrete routing rule — use this before listing all games when the slug is unknown, and set types: ["games"] to keep responses small.

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