Lichess

User Performance

user_performance

Read-onlyIdempotent

Single-variant performance + best rated game for a user.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "perf": "blitz",
      "username": "DrNykterstein"
    },
    "name": "user_performance"
  }
}

Input Schema

Name	Required	Description	Default
`perf`	Yes	bullet \| blitz \| rapid \| classical \| correspondence \| chess960 \| crazyhouse \| antichess \| atomic \| horde \| kingOfTheHill \| racingKings \| threeCheck \| ultraBullet
`username`	Yes

Output Schema

Name	Required	Description
`rank`	No	Ranking in variant
`stat`	No
`bestWins`	No	Best wins
`percentile`	No	Percentile ranking

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 29, 2026
- changedOutput schema / properties / percentile / type
```
Previous value: -"number"New value: +[
+  "number",
+  "null"
+]
```
- changedOutput schema / properties / rank / type
```
Previous value: -"number"New value: +[
+  "number",
+  "null"
+]
```

Changed1 schema field changedJul 30, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "perf": "blitz",
-    "username": "hikaru"
-  },
-  {
-    "perf": "classical",
-    "username": "magnuschess"
-  }
-]New value: +[
+  {
+    "perf": "blitz",
+    "username": "DrNykterstein"
+  },
+  {
+    "perf": "bullet",
+    "username": "Zhigalko_Sergei"
+  }
+]

Changed2 schema fields changedMay 27, 2026

addedInput schema / examples

Added value: +[
+  {
+    "perf": "blitz",
+    "username": "hikaru"
+  },
+  {
+    "perf": "classical",
+    "username": "magnuschess"
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "bestWins": {
+      "description": "Best wins",
+      "items": {
+        "properties": {
+          "gameId": {
+            "description": "Game ID",
+            "type": "string"
+          },
+          "opponentName": {
+            "description": "Opponent username",
+            "type": "string"
+          },
+          "opponentRating": {
+            "description": "Opponent rating",
+            "type": "number"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "percentile": {
+      "description": "Percentile ranking",
+      "type": "number"
+    },
+    "rank": {
+      "description": "Ranking in variant",
+      "type": "number"
+    },
+    "stat": {
+      "properties": {
+        "plays": {
+          "description": "Games played",
+          "type": "number"
+        },
+        "prog": {
+          "description": "Progress",
+          "type": "number"
+        },
+        "prov": {
+          "description": "Provisional",
+          "type": "boolean"
+        },
+        "rating": {
+          "description": "Current rating",
+          "type": "number"
+        },
+        "rd": {
+          "description": "Rating deviation",
+          "type": "number"
+        },
+        "score": {
+          "description": "Score",
+          "type": "number"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

First observedMay 13, 2026

TDQS

C2.8/5.0

Behavior3/5

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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is clear. The description adds that results cover a single variant and include a best-rated game, but it does not disclose error behavior, privacy constraints, or rate limits.

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 description is a single front-loaded sentence with no wasted words. It is appropriately concise for a simple read-only tool, though its terseness borders on under-specification.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Since an output schema exists and annotations cover the safety profile, the description need not explain return values or side-effect behavior. Still, it omits usage context and does not help an agent choose this tool over related user or status tools.

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

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 50%: perf lists allowed values, but username is undocumented in the schema. The description hints at 'single-variant' (perf) and 'for a user' (username) but adds no format or validity details, so it does not compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource as user performance data plus a best-rated game, and scopes it to a single variant. However, it lacks a specific verb and does not distinguish this tool from siblings like user, users, or user_status, leaving the agent to infer the exact operation.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. The only implied usage is that it retrieves performance for one chess variant of a given user.

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

All Lichess 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.