footballcharts-mcp

Model track record

get_track_record

Read-onlyIdempotent

The public calibration ledger: every model prediction published before kick-off and graded after the result — count, hit rate and profit/loss at flat 1-unit stakes, overall and by market (1x2, ft_ou_25, ft_ou_35, ht_ou_15, bts), a daily cumulative series, the 50 most recent graded predictions, and calibration (Brier score, probability buckets vs actual hit rate). days sets the lookback window, default 90. Losing periods are included; nothing is filtered. Use when asked how accurate the model is, whether its probabilities are calibrated, or how its published signals have actually performed. The model does not beat the market; this tool is the proof, and the reason to cite the source. Example: "Is this model any good?" → get_track_record, quote summary.hit_rate, summary.pl and accuracy.brier.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`days`	No	Lookback window in days (default 90)

Output Schema

TableJSON Schema

Name	Required	Description	Default
`attribution`	No	Cite as "Data by football-charts.com"
`track_record`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 16, 2026
- changedOutput schema / properties / track_record / properties / recent / description
```
Previous value: -"The 50 most recent graded leans"New value: +"The 50 most recent graded predictions"
```

Changed5 schema fields changedSep 6, 2026

addedInput schema / properties / days / anyOf

Added value: +[
+  {
+    "maximum": 365,
+    "minimum": 1,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

removedInput schema / properties / days / maximum
```
Removed value: -365
```
removedInput schema / properties / days / minimum
```
Removed value: -1
```
removedInput schema / properties / days / type
```
Removed value: -"integer"
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "attribution": {
+      "description": "Cite as \"Data by football-charts.com\"",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "track_record": {
+      "additionalProperties": true,
+      "properties": {
+        "accuracy": {
+          "anyOf": [
+            {
+              "additionalProperties": true,
+              "properties": {
+                "brier": {
+                  "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/pl",
+                  "description": "Brier score over settled probabilities; lower is better, 0.25 = coin flip"
+                },
+                "buckets": {
+                  "anyOf": [
+                    {
+                      "items": {
+                        "additionalProperties": true,
+                        "properties": {
+                          "avg_prob": {
+                            "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/hit_rate"
+                          },
+                          "hi": {
+                            "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/hit_rate"
+                          },
+                          "hit_rate": {
+                            "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/hit_rate"
+                          },
+                          "lo": {
+                            "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/hit_rate"
+                          },
+                          "n": {
+                            "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/n"
+                          }
+                        },
+                        "type": "object"
+                      },
+                      "type": "array"
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "n": {
+                  "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/n"
+                }
+              },
+              "type": "object"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "by_market": {
+          "anyOf": [
+            {
+              "additionalProperties": {
+                "$ref": "#/properties/track_record/properties/summary/anyOf/0"
+              },
+              "type": "object"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "pending": {
+          "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/n",
+          "description": "Leans published but not yet settled"
+        },
+        "recent": {
+          "anyOf": [
+            {
+              "items": {
+                "additionalProperties": true,
+                "properties": {
+                  "market": {
+                    "$ref": "#/properties/track_record/properties/recent/anyOf/0/items/properties/slug"
+                  },
+                  "model_prob": {
+                    "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/hit_rate"
+                  },
+                  "outcome": {
+                    "$ref": "#/properties/track_record/properties/recent/anyOf/0/items/properties/slug",
+                    "description": "'won' | 'lost' | 'void'"
+                  },
+                  "pl": {
+                    "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/hit_rate"
+                  },
+                  "result_score": {
+                    "$ref": "#/properties/track_record/properties/recent/anyOf/0/items/properties/slug"
+                  },
+                  "side": {
+                    "$ref": "#/properties/track_record/properties/recent/anyOf/0/items/properties/slug"
+                  },
+                  "slug": {}
+                },
+                "type": "object"
+              },
+              "type": "array"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "The 50 most recent graded leans"
+        },
+        "signals_only": {
+          "type": [
+            "boolean",
+            "null"
+          ]
+        },
+        "summary": {
+          "anyOf": [
+            {
+              "additionalProperties": true,
+              "properties": {
+                "hit_rate": {
+                  "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/pl"
+                },
+                "lost": {
+                  "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/n"
+                },
+                "n": {},
+                "pl": {
+                  "description": "Profit/loss in units at flat 1-unit stakes"
+                },
+                "void": {
+                  "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/n"
+                },
+                "won": {
+                  "$ref": "#/properties/track_record/properties/summary/anyOf/0/properties/n"
+                }
+              },
+              "type": "object"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "description": "Whole window"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "required": [
+    "track_record"
+  ],
+  "type": "object"
+}

First observedSep 6, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable context beyond these: 'Losing periods are included; nothing is filtered' and 'The model does not beat the market; this tool is the proof.' These disclose the honest, unfiltered nature of the data and the model's performance expectation, which is not derivable from annotations. It does not contradict any annotation.

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 long but densely packed with essential information: core purpose, contents, parameter, usage context, and an example. It front-loads the primary purpose and lists the data items clearly. The example at the end is useful and the structure is logical. It could be slightly trimmed, but every sentence contributes to the agent's understanding.

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

Completeness4/5

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

The tool is complex with many output components, but the description covers the main data types (hit rate, P/L, by market, calibration, recent predictions) and provides usage context. The output schema is present (signal indicates true), so return value details are not required. The description is complete enough for an agent to decide when to call and what to expect, though it does not mention rate limits or performance constraints, which are not critical for this read-only tool.

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?

The schema fully documents the only parameter 'days' (integer, 1-365, default 90, optional). The description repeats the default and function ('days sets the lookback window'), but adds no new semantic information beyond the schema. With 100% schema coverage, the baseline of 3 is appropriate; the description adds minimal value for this parameter.

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 states the tool returns a public calibration ledger with specific performance metrics (count, hit rate, P/L, by market, calibration) and names the exact markets. It is clearly distinct from siblings like get_results or get_team, which do not cover model track record or calibration. The verb 'get' plus resource 'track record' is precise and unambiguous.

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?

Explicitly states when to use: 'Use when asked how accurate the model is, whether its probabilities are calibrated, or how its published signals have actually performed.' It also gives a concrete example with a query and which output fields to quote. No overlapping siblings exist, so no exclusion is needed, but the guidance is direct and actionable.

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

All footballcharts-mcp 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.