Housing Intel

Case Shiller Metro Compare

case_shiller_metro_compare

Read-onlyIdempotent

Compare Case-Shiller home price indices across multiple US metros in one call (the 20-city composite). For each metro returns latest level, 3-month change, 12-month change, all-time peak, drawdown from peak, and a softening flag. Output also ranks metros softest → strongest. Use for "which metros are softening", "Case-Shiller for [list of cities]", "compare housing prices in X, Y, Z" queries — picks the right per-metro FRED series IDs (DNXRSA, PHXRSA, TPXRSA, etc.) so callers don't have to. Available metros: Atlanta, Boston, Charlotte, Chicago, Cleveland, Dallas, Denver, Detroit, Las Vegas, Los Angeles, Miami, Minneapolis, New York, Phoenix, Portland, San Diego, San Francisco, Seattle, Tampa, Washington DC. NOT A CURRENT-MARKET READ: Case-Shiller is monthly, published on a roughly two-month lag, and each value is a three-month moving average — so the newest observation is typically 90-120 days old and describes a trailing quarter. The freshness block states the exact age of the call you made.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`metros`	Yes	Metro names, case-insensitive. Example: ["Denver", "Phoenix", "Tampa", "Charlotte"]. Pass any subset of the 20-city composite.
`_fredKey`	No	FRED API key (https://fred.stlouisfed.org/docs/api/api_key.html). Platform key used if omitted.

Output Schema

TableJSON Schema

Name	Required	Description
`metros`	No	Ranked metros from softest to strongest
`freshness`	No
`methodology`	No
`softest_to_strongest`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed24 schema fields changedSep 27, 2026

removedOutput schema / properties / error

Removed value: -{
-  "description": "Error message if request failed",
-  "type": "string"
-}

addedOutput schema / properties / freshness

Added value: +{
+  "properties": {
+    "age_days": {
+      "type": "number"
+    },
+    "as_of": {
+      "type": "string"
+    },
+    "cadence": {
+      "type": "string"
+    },
+    "newest_observation_date": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "oldest_observation_date": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "release_schedule": {
+      "type": "string"
+    },
+    "smoothing": {
+      "type": "string"
+    },
+    "statement": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / methodology
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / metros / items / properties / all_time_peak

Removed value: -{
-  "description": "Highest value ever recorded",
-  "type": "number"
-}

addedOutput schema / properties / metros / items / properties / change_12m_pct
```
Added value: +{
+  "type": "number"
+}
```

removedOutput schema / properties / metros / items / properties / change_12mo

Removed value: -{
-  "description": "12-month change in index points",
-  "type": "number"
-}

addedOutput schema / properties / metros / items / properties / change_3m_pct
```
Added value: +{
+  "type": "number"
+}
```

removedOutput schema / properties / metros / items / properties / change_3mo

Removed value: -{
-  "description": "3-month change in index points",
-  "type": "number"
-}

removedOutput schema / properties / metros / items / properties / current

Removed value: -{
-  "description": "Latest Case-Shiller index value",
-  "type": "number"
-}

removedOutput schema / properties / metros / items / properties / drawdown_from_peak

Removed value: -{
-  "description": "Percent decline from all-time peak",
-  "type": "number"
-}

addedOutput schema / properties / metros / items / properties / drawdown_from_peak_pct
```
Added value: +{
+  "type": "number"
+}
```
addedOutput schema / properties / metros / items / properties / latest_age_days
```
Added value: +{
+  "type": [
+    "number",
+    "null"
+  ]
+}
```
addedOutput schema / properties / metros / items / properties / latest_date
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
addedOutput schema / properties / metros / items / properties / latest_value
```
Added value: +{
+  "type": [
+    "number",
+    "null"
+  ]
+}
```
addedOutput schema / properties / metros / items / properties / matched_name
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / metros / items / properties / metro

Removed value: -{
-  "description": "Metro name",
-  "type": "string"
-}

removedOutput schema / properties / metros / items / properties / pct_change_12mo

Removed value: -{
-  "description": "12-month percent change",
-  "type": "number"
-}

removedOutput schema / properties / metros / items / properties / pct_change_3mo

Removed value: -{
-  "description": "3-month percent change",
-  "type": "number"
-}

addedOutput schema / properties / metros / items / properties / peak_date
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
addedOutput schema / properties / metros / items / properties / peak_value
```
Added value: +{
+  "type": [
+    "number",
+    "null"
+  ]
+}
```
addedOutput schema / properties / metros / items / properties / requested
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / metros / items / properties / trend

Removed value: -{
-  "description": "Trend label based on recent values",
-  "enum": [
-    "rising",
-    "falling",
-    "stable"
-  ],
-  "type": "string"
-}

removedOutput schema / properties / snapshot_date

Removed value: -{
-  "description": "Today's date in YYYY-MM-DD format",
-  "type": "string"
-}

addedOutput schema / properties / softest_to_strongest

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Changed1 schema field changedAug 4, 2026

changedInput schema / examples

Previous value: -[
-  {
-    "metros": [
-      "Denver",
-      "Phoenix",
-      "Tampa",
-      "Charlotte"
-    ]
-  },
-  {
-    "_fredKey": "your-housing-intel-api-key",
-    "metros": [
-      "San Francisco",
-      "Los Angeles",
-      "Seattle"
-    ]
-  }
-]New value: +[
+  {
+    "metros": [
+      "Denver",
+      "Phoenix",
+      "Tampa",
+      "Charlotte"
+    ]
+  },
+  {
+    "metros": [
+      "San Francisco",
+      "Los Angeles",
+      "Seattle"
+    ]
+  }
+]

Changed16 schema fields changedMay 24, 2026

addedInput schema / examples

Added value: +[
+  {
+    "metros": [
+      "Denver",
+      "Phoenix",
+      "Tampa",
+      "Charlotte"
+    ]
+  },
+  {
+    "_fredKey": "your-housing-intel-api-key",
+    "metros": [
+      "San Francisco",
+      "Los Angeles",
+      "Seattle"
+    ]
+  }
+]

addedOutput schema / properties / error

Added value: +{
+  "description": "Error message if request failed",
+  "type": "string"
+}

changedOutput schema / properties / metros / items / properties / all_time_peak / description

Previous value: -"Peak index value in series history"New value: +"Highest value ever recorded"

removedOutput schema / properties / metros / items / properties / change_12m

Removed value: -{
-  "description": "12-month change in index points",
-  "type": "number"
-}

addedOutput schema / properties / metros / items / properties / change_12mo

Added value: +{
+  "description": "12-month change in index points",
+  "type": "number"
+}

removedOutput schema / properties / metros / items / properties / change_3m

Removed value: -{
-  "description": "3-month change in index points",
-  "type": "number"
-}

addedOutput schema / properties / metros / items / properties / change_3mo

Added value: +{
+  "description": "3-month change in index points",
+  "type": "number"
+}

changedOutput schema / properties / metros / items / properties / drawdown_from_peak / description

Previous value: -"Percentage below all-time peak"New value: +"Percent decline from all-time peak"

addedOutput schema / properties / metros / items / properties / pct_change_12mo

Added value: +{
+  "description": "12-month percent change",
+  "type": "number"
+}

addedOutput schema / properties / metros / items / properties / pct_change_3mo

Added value: +{
+  "description": "3-month percent change",
+  "type": "number"
+}

changedOutput schema / properties / metros / items / properties / series_id / description
```
Previous value: -"FRED series ID"New value: +"FRED series ID (e.g., DNXRSA)"
```

changedOutput schema / properties / metros / items / properties / softening / description

Previous value: -"True if recent trend shows softening"New value: +"True if 12-month change is negative"

addedOutput schema / properties / metros / items / properties / trend

Added value: +{
+  "description": "Trend label based on recent values",
+  "enum": [
+    "rising",
+    "falling",
+    "stable"
+  ],
+  "type": "string"
+}

removedOutput schema / properties / ranking_note

Removed value: -{
-  "description": "Explanation of ranking methodology",
-  "type": "string"
-}

changedOutput schema / properties / snapshot_date / description

Previous value: -"ISO date of snapshot"New value: +"Today's date in YYYY-MM-DD format"

removedOutput schema / required

Removed value: -[
-  "snapshot_date",
-  "metros"
-]

Changed1 schema field changedMay 22, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "metros": {
+      "description": "Ranked metros from softest to strongest",
+      "items": {
+        "properties": {
+          "all_time_peak": {
+            "description": "Peak index value in series history",
+            "type": "number"
+          },
+          "change_12m": {
+            "description": "12-month change in index points",
+            "type": "number"
+          },
+          "change_3m": {
+            "description": "3-month change in index points",
+            "type": "number"
+          },
+          "current": {
+            "description": "Latest Case-Shiller index value",
+            "type": "number"
+          },
+          "drawdown_from_peak": {
+            "description": "Percentage below all-time peak",
+            "type": "number"
+          },
+          "metro": {
+            "description": "Metro name",
+            "type": "string"
+          },
+          "series_id": {
+            "description": "FRED series ID",
+            "type": "string"
+          },
+          "softening": {
+            "description": "True if recent trend shows softening",
+            "type": "boolean"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "ranking_note": {
+      "description": "Explanation of ranking methodology",
+      "type": "string"
+    },
+    "snapshot_date": {
+      "description": "ISO date of snapshot",
+      "type": "string"
+    }
+  },
+  "required": [
+    "snapshot_date",
+    "metros"
+  ],
+  "type": "object"
+}

AddedMay 13, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare it read-only, idempotent, and non-destructive. The description adds substantial behavioral context beyond that: the two-month publication lag, three-month moving average, typically 90-120 day old observations, and the `freshness` block that reports exact data age. It also discloses that it picks the correct per-metro FRED series IDs automatically.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence earns its place: purpose, output metrics, example queries, available metro list, and a crucial freshness caveat. It is front-loaded with the core action and the most decision-relevant caveat is clearly flagged with 'NOT A CURRENT-MARKET READ.'

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?

Covers what the tool returns (metrics, ranking, freshness), which inputs are valid, why the data age is important, and how the caller benefits (no need to know FRED series IDs). Combined with the existing output schema and annotations, nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so the baseline is 3. The description goes further by listing the 20 available metros, noting case-insensitivity, explicitly allowing any subset, and clarifying that series ID selection is handled for the caller. This adds genuine value beyond the schema's plain parameter descriptions.

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 a specific verb and resource: 'Compare Case-Shiller home price indices across multiple US metros in one call (the 20-city composite).' It lists the exact metrics returned and the query patterns it addresses, making it clearly distinct from sibling housing tools.

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?

Provides explicit example query phrasings ('which metros are softening', 'compare housing prices in X, Y, Z') and explicitly warns it is NOT a current-market read due to the monthly lag and moving-average nature. This gives clear when-to-use and when-not-to-use guidance without naming alternatives.

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

All Housing Intel 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.