NakamotoNotes Bitcoin Barometer

Heat Score history

get_history

Read-onlyIdempotent

Heat Score history from the public daily history. from is required (YYYY-MM-DD), to defaults to the last day. interval day|week|month|auto (auto picks the finest that fits 400 points); max_points (1-400) caps the points: auto uses 180 by default, and with max_points the latest points are kept and truncated is set. A summary covers the whole range.

Input Schema

Name	Required	Description
`to`	No	Last day, YYYY-MM-DD (default: last available day)
`from`	Yes	First day, YYYY-MM-DD
`interval`	No	Point size (default auto)
`max_points`	No	Most points to return; older points are dropped and truncated is set

Output Schema

Name	Required	Description	Default
`to`	Yes
`from`	Yes
`count`	Yes
`points`	Yes
`license`	No
`summary`	Yes
`interval`	Yes
`dataRange`	No
`truncated`	No
`limitation`	No
`methodology`	No
`omittedPoints`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 19, 2026

addedInput schema / properties / max_points

Added value: +{
+  "description": "Most points to return; older points are dropped and truncated is set",
+  "maximum": 400,
+  "minimum": 1,
+  "type": "integer"
+}

addedOutput schema / properties / omittedPoints
```
Added value: +{
+  "type": "integer"
+}
```
addedOutput schema / properties / truncated
```
Added value: +{
+  "type": "boolean"
+}
```

Changed4 schema fields changedOct 18, 2026

addedInput schema / properties / interval

Added value: +{
+  "description": "Point size (default auto)",
+  "enum": [
+    "day",
+    "week",
+    "month",
+    "auto"
+  ],
+  "type": "string"
+}

changedInput schema / properties / to / description

Previous value: -"Last day, YYYY-MM-DD"New value: +"Last day, YYYY-MM-DD (default: last available day)"

changedInput schema / required

Previous value: -[
-  "from",
-  "to"
-]New value: +[
+  "from"
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "type": "integer"
+    },
+    "dataRange": {
+      "type": "object"
+    },
+    "from": {
+      "type": "string"
+    },
+    "interval": {
+      "type": "string"
+    },
+    "license": {
+      "type": "string"
+    },
+    "limitation": {
+      "type": "string"
+    },
+    "methodology": {
+      "type": "string"
+    },
+    "points": {
+      "items": {
+        "properties": {
+          "date": {
+            "type": "string"
+          },
+          "score": {
+            "type": "integer"
+          },
+          "zone": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "date",
+          "score",
+          "zone"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "summary": {
+      "properties": {
+        "days": {
+          "type": "integer"
+        },
+        "daysPerZone": {
+          "type": "object"
+        },
+        "max": {
+          "type": "number"
+        },
+        "mean": {
+          "type": "number"
+        },
+        "min": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "min",
+        "max",
+        "mean",
+        "days",
+        "daysPerZone"
+      ],
+      "type": "object"
+    },
+    "to": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "from",
+    "to",
+    "interval",
+    "count",
+    "points",
+    "summary"
+  ],
+  "type": "object"
+}

First observedOct 17, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description only needed to add behavior beyond that — and it does: the 'auto picks the finest that fits 400 points' rule, the 180-point default, and the fact that max_points truncates from the oldest end and sets a 'truncated' flag. That truncation disclosure is genuinely useful for interpreting results. It does not cover rate limits or the public-data freshness caveat.

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 resource is front-loaded and every sentence carries information; there is no filler. The parameter clauses are dense and slightly run-on, which costs a point but not comprehension.

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?

With an output schema present, return values need not be described, and the description still notes that a summary covers the whole range. Between the annotations, full schema coverage, and the auto/truncation rules, an agent has enough to call it correctly; only edge behavior (e.g. what 'truncated' means downstream) is left implicit.

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 100%, so baseline is 3, but the description goes further than the schema on two params: it explains that interval=auto selects the finest resolution fitting 400 points, and that auto uses max_points=180 while an explicit max_points keeps the latest points and sets a truncation flag. That is real added semantics over the terse schema strings.

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

Purpose4/5

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

States a specific resource with scope: 'Heat Score history from the public daily history,' so an agent knows it retrieves a time-series rather than a definition (explain_indicator) or a current-state view (get_market_snapshot). The verb is implicit in 'history' rather than stated outright, and it never names a sibling, so it falls short of a 5.

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

Usage Guidelines3/5

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

Usage is implied by the parameter framing ('from is required', 'to defaults to the last day') rather than stated as when-to-use guidance. There is no explicit condition distinguishing this from explain_indicator or get_market_snapshot, but the retrieval context is clear enough to act on.

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

All NakamotoNotes Bitcoin Barometer 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.