Skip to main content
Glama

Find co-op games like another

find_similar_coop_games
Read-onlyIdempotent

Find co-op games like one the group already enjoys, from CoopGamesDB's catalogue: the games sharing the most genres, themes and ways to play together with it, the more popular first among equals, optionally only those for the group's size, platforms, way of playing and price. Use it for "games like Lethal Company", "co-op games similar to It Takes Two for 2 players" or "what should we play after Valheim?". Each game says what it shares with the one named, with its players, platforms, price and Steam reviews. Each game links its CoopGamesDB page.

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": {
      "game": "<game>"
    },
    "name": "find_similar_coop_games"
  }
}

Input Schema

NameRequiredDescriptionDefault
gameYesThe game the group enjoys, as people write it, such as "Lethal Company".
limitNoHow many games to list (6 unless asked).
modesNoHow the group plays together; a game must offer every one listed: "online", "local" (same couch), "split" (split screen), "lan".
priceNoThe most one copy may cost, in US dollars on Steam’s US store (sale prices count): "free", "under10", "under20" or "any".
playersNoHow many people will play together: only games that fit a group this size.
platformsNoPlatforms the group plays on: games on at least one of them. "pc" covers Steam and Windows.

Output Schema

NameRequiredDescriptionDefault
gameYes
foundYes
gamesYes
groupSizeYes
suggestionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / platforms / items / enum
      Previous value: -[
      -  "pc",
      -  "ps5",
      -  "xbox",
      -  "switch",
      -  "mac",
      -  "linux",
      -  "mobile",
      -  "web"
      -]New value: +[
      +  "pc",
      +  "ps5",
      +  "xbox",
      +  "switch",
      +  "mac",
      +  "linux",
      +  "mobile",
      +  "ios",
      +  "android",
      +  "web"
      +]
    • changedInput schema / properties / platforms / maxItems
      Previous value: -8New value: +10
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower; the description still adds the ordering semantics (most shared traits first, popularity breaking ties) and notes that each result explains what it shares with the seed game. Return-shape details are partially redundant with the existing output schema, which keeps it from a 5.

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 core purpose and ranking rule are front-loaded in the first sentence, with filters and use cases following. It is dense but every clause carries information; the embedded example queries are justified by how much they disambiguate. Slightly long for what remains a single-purpose lookup, but not padded.

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 annotations covering safety profile, an output schema covering return shape, and full schema coverage on all six parameters, the description only needs to supply purpose, ranking behavior and trigger examples — and it does all three. An agent has everything needed to decide to call it and how to interpret the ordering.

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 description coverage is 100%, including enum value glosses for modes, price and platforms, so the baseline is 3. The description restates the filter dimensions at a high level ("the group's size, platforms, way of playing and price") but adds no semantics beyond the schema — notably it does not clarify the AND-vs-OR behavior, which the schema itself handles.

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?

The description names a specific verb and resource ("Find co-op games like one the group already enjoys") and goes further by stating the ranking logic: games sharing the most genres, themes and ways to play, with popularity as tiebreak. That similarity framing cleanly separates it from the sibling browse/list/lookup tools (find_coop_games, list_new_and_upcoming_coop_games, get_coop_game) without needing to name them.

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?

Three concrete example queries ("games like Lethal Company", "co-op games similar to It Takes Two for 2 players", "what should we play after Valheim?") make the intended trigger unmistakable, and the phrase "optionally only those for the group's size, platforms..." signals when the optional filters apply. It stops short of an explicit exclusion such as "use find_coop_games when you have no reference title", so it lands at 4 rather than 5.

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