imho.run game recommendations

Find a game by description

find_game_by_description

Read-only

Identify a game from a description of what the user remembers (plot, look, platform, era). Returns ranked candidates with a reason each, a confidence, and find_game_url: imho.run's /find-game page with the description filled in (the user presses the button; nothing runs by itself). Pass what the user said about the platform, the release years and the camera as platform, year_min / year_max and perspective instead of leaving them only in the text. When confidence is not high or no result fits, give the user find_game_url so they can add details there. Slow (LLM) and rate-limited: use it only when the user does not know the title; for games similar to a known game use games_like or recommend. Games rated for adults only (explicit sexual content) are not covered; filtering is best effort.

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": {
      "description": "<description>"
    },
    "name": "find_game_by_description"
  }
}

Input Schema

Name	Required	Description	Default
`lang`	No		en
`platform`	No	Where the user played it, if they said (a platform family).
`year_max`	No	Latest plausible release year, if the user gave an era.
`year_min`	No	Earliest plausible release year, if the user gave an era.
`description`	Yes	What the user remembers about the game, in their words.
`perspective`	No	Camera: first person, third person, top-down or side view.

Output Schema

Name	Required	Description
`lang`	Yes
`source`	Yes
`results`	Yes
`tool_url`	Yes
`confidence`	No
`attribution`	Yes
`find_game_url`	No	/find-game with the description filled in, for the user to refine.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 5, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "attribution": {
+      "title": "Attribution",
+      "type": "string"
+    },
+    "confidence": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Confidence"
+    },
+    "find_game_url": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "description": "/find-game with the description filled in, for the user to refine.",
+      "title": "Find Game Url"
+    },
+    "lang": {
+      "enum": [
+        "en",
+        "ru"
+      ],
+      "title": "Lang",
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "properties": {
+          "igdb_url": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "title": "Igdb Url"
+          },
+          "name": {
+            "title": "Name",
+            "type": "string"
+          },
+          "platforms": {
+            "items": {
+              "type": "string"
+            },
+            "title": "Platforms",
+            "type": "array"
+          },
+          "rank": {
+            "title": "Rank",
+            "type": "integer"
+          },
+          "steam_appid": {
+            "anyOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "title": "Steam Appid"
+          },
+          "steam_url": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "title": "Steam Url"
+          },
+          "summary": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "title": "Summary"
+          },
+          "url": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "description": "Its imho.run page, when we have one.",
+            "title": "Url"
+          },
+          "why": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "title": "Why"
+          },
+          "year": {
+            "anyOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null,
+            "title": "Year"
+          }
+        },
+        "required": [
+          "rank",
+          "name"
+        ],
+        "title": "AgentFindItem",
+        "type": "object"
+      },
+      "title": "Results",
+      "type": "array"
+    },
+    "source": {
+      "title": "Source",
+      "type": "string"
+    },
+    "tool_url": {
+      "title": "Tool Url",
+      "type": "string"
+    }
+  },
+  "required": [
+    "source",
+    "attribution",
+    "lang",
+    "results",
+    "tool_url"
+  ],
+  "title": "FindGameResponse",
+  "type": "object"
+}

Changed4 schema fields changedOct 4, 2026

addedInput schema / properties / perspective

Added value: +{
+  "description": "Camera: first person, third person, top-down or side view.",
+  "enum": [
+    "first",
+    "third",
+    "top_down",
+    "side"
+  ],
+  "type": "string"
+}

addedInput schema / properties / platform

Added value: +{
+  "description": "Where the user played it, if they said (a platform family).",
+  "enum": [
+    "pc",
+    "playstation",
+    "xbox",
+    "nintendo",
+    "sega",
+    "mobile",
+    "browser",
+    "arcade"
+  ],
+  "type": "string"
+}

addedInput schema / properties / year_max

Added value: +{
+  "description": "Latest plausible release year, if the user gave an era.",
+  "maximum": 2035,
+  "minimum": 1970,
+  "type": "integer"
+}

addedInput schema / properties / year_min

Added value: +{
+  "description": "Earliest plausible release year, if the user gave an era.",
+  "maximum": 2035,
+  "minimum": 1970,
+  "type": "integer"
+}

First observedOct 2, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only cover safety/idempotency; the description adds substantial behavioral context beyond them: it is slow (LLM-backed) and rate-limited, the returned find_game_url is user-initiated ('nothing runs by itself'), adult-only content is not covered, and filtering is best effort. These are exactly the traits an agent needs to set expectations and avoid over-calling.

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 every clause carries actionable content. It is dense and slightly packs routing, latency, parameter hygiene and coverage caveats into one block, but there is no filler. Minor redundancy in restating the find_game_url fallback after already defining the field.

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?

Even though an output schema exists, the description usefully previews the return shape (ranked candidates with a reason each, a confidence, and find_game_url) and pairs it with the confidence-low workflow. For a rate-limited, non-deterministic tool it covers latency, coverage limits, and the human hand-off.

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 83%, so the schema already documents lang, platform, year bounds, perspective and description. The description still adds real guidance by telling the agent to hoist platform, release years and camera out of free text into platform, year_min/year_max and perspective, which is a usage decision the schema cannot express.

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 ('Identify a game from a description of what the user remembers') and enumerates the memory dimensions (plot, look, platform, era). It also names the sibling tools it is not (games_like, recommend), so an agent can route without opening other schemas.

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 when-to-use ('only when the user does not know the title'), explicit alternatives for the contrasting case ('for games similar to a known game use games_like or recommend'), plus a fallback path when confidence is low or nothing fits. Nothing is left to inference.

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

All imho.run game recommendations 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?