ArcadeIndex

Search games

search_games

Read-onlyIdempotent

Find web games from a natural-language query plus optional filters (genre, mood, session length, players, quality, content rating, difficulty, inputs). Phrases like 'for kids', '2 player', 'under 10 minutes', 'not a shooter', 'easy' or 'chill' are turned into filters (echoed as interpreted_filters); explicit params win. 'like {title}' or 'similar to {title}' naming a game in the catalog returns that game's games_like results (anchor is set). Returns only published, playable games verified within the last 8 days (listing-only games with include_listing_only=true; plays=here or plays=developer_site picks one kind). content_rating_max defaults to teen. Zero results is a success with code NO_MATCHES and up to 3 executed relaxations whose args you can call again (with the tool named in tool, when set). Quote match_reasons and link play_url; render 'via ArcadeIndex' per the attribution block.

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": "search_games"
  }
}

Input Schema

Name	Required	Description	Default
`mood`	No
`genre`	No
`limit`	No
`plays`	No	here: only games that play embedded (on ArcadeIndex and in the in-chat player); developer_site: only games that play on the developer's own site (implies include_listing_only).
`query`	Yes	Natural-language query, e.g. 'easy 2 player game for kids'.
`inputs`	No
`players`	No
`interpret`	No	Rule-based intent extraction (agent-api §7).
`difficulty`	No
`min_quality`	No
`exclude_genres`	No
`content_rating_max`	No		teen
`session_length_max`	No
`include_listing_only`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 25, 2026

changedInput schema / properties / content_rating_max / enum

Previous value: -[
-  "everyone",
-  "everyone_10",
-  "teen",
-  "mature"
-]New value: +[
+  "everyone",
+  "everyone_10",
+  "teen"
+]

First observedOct 23, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the readOnly/idempotent annotations: discloses the freshness window (verified within last 8 days), the default content_rating_max of teen, the published/playable constraint, the here-vs-developer_site listing split, and detailed NO_MATCHES zero-result semantics including numbered relaxations.

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-loads the core action and query interpretation first, then layers on freshness and error semantics. It is dense and parenthetical-heavy but every clause carries operational value; only minor tightening would help.

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 14-parameter tool with low schema coverage, the description covers defaults, decomposition rules, delegation to games_like, zero-result handling, and attribution obligations. With an output schema present, return shapes need no explanation, so nothing essential 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?

With only 21% schema coverage, the description carries most of the load and does well: it maps natural-language phrases to genre/mood/players/session_length/difficulty filters, clarifies include_listing_only and plays interplay, and flags default content_rating_max. It doesn't individually explain min_quality, interpret, or limit, but the overall semantic coverage across parameters is high.

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 (find web games from a natural-language query) and immediately distinguishes its filtering role from siblings, calling out that 'like {title}' delegates to games_like results. An agent can tell exactly what this tool is versus games_like, get_game, trending, etc.

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?

Explains when to rely on natural-language interpretation versus explicit params ('explicit params win'), when games_like routing kicks in ('anchor is set'), and how to escalate on empty results (NO_MATCHES plus up to 3 relaxations with switchable tool). This is explicit when-to-use guidance tied to observable state.

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

All ArcadeIndex tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?