whale-insights

status

Read-onlyIdempotent

Check live API & system health — operational/degraded verdict, per-source freshness, MCP tool count — Public health status of all CryptoWhaleInsights data sources, MCP server, and OpenAPI spec. Returns overall verdict (operational/degraded/outage), per-source health with age in seconds, recent 24-hour error count, MCP tool count, and OpenAPI path count. Useful for AI agents and developers to verify the platform is live before making requests. Cached ~30s.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description
`overall`	No
`sources`	No
`checkedAt`	No
`freshness`	No	Per-endpoint cache freshness data. Each entry describes how stale a cached API response is, so AI agents can decide whether to trust the data without making an extra request.
`attribution`	No
`mcpToolCount`	No
`openApiPaths`	No
`errorCount24h`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "attribution": {
+      "$ref": "#/components/schemas/Attribution"
+    },
+    "checkedAt": {
+      "format": "date-time",
+      "type": "string"
+    },
+    "errorCount24h": {
+      "type": "number"
+    },
+    "freshness": {
+      "description": "Per-endpoint cache freshness data. Each entry describes how stale a cached API response is, so AI agents can decide whether to trust the data without making an extra request.",
+      "items": {
+        "properties": {
+          "cacheAgeSeconds": {
+            "description": "How many seconds have elapsed since the cache was last populated. Null when the cache has never been populated (cold start).",
+            "nullable": true,
+            "type": "number"
+          },
+          "cacheIntervalSeconds": {
+            "description": "How often this endpoint's data is refreshed, in seconds.",
+            "type": "number"
+          },
+          "endpoint": {
+            "description": "The API path this freshness entry applies to (e.g. '/api/public/platform-stats').",
+            "type": "string"
+          },
+          "label": {
+            "description": "Human-readable name for the endpoint (e.g. 'Platform Stats').",
+            "type": "string"
+          },
+          "status": {
+            "description": "'fresh' = within the normal refresh window; 'stale' = older than the expected interval; 'cold' = cache has never been populated.",
+            "enum": [
+              "fresh",
+              "stale",
+              "cold"
+            ],
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "mcpToolCount": {
+      "type": "number"
+    },
+    "openApiPaths": {
+      "type": "number"
+    },
+    "overall": {
+      "enum": [
+        "operational",
+        "degraded",
+        "outage"
+      ],
+      "type": "string"
+    },
+    "sources": {
+      "items": {
+        "properties": {
+          "ageSeconds": {
+            "nullable": true,
+            "type": "number"
+          },
+          "lastSuccess": {
+            "format": "date-time",
+            "nullable": true,
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "status": {
+            "enum": [
+              "healthy",
+              "stale",
+              "failing",
+              "unknown"
+            ],
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

AddedJun 21, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds meaningful context beyond that: cached ~30s, per-source age in seconds, 24-hour error counts, and the specific output categories. This fully discloses the tool's observable behavior without contradicting annotations.

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 front-loaded with the core verdict and includes the key output fields, use case, and caching detail in a compact form. There is minor redundancy between the opening summary, the 'Public health status' sentence, and the detailed return list, but nothing is extraneous or bloated.

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?

For a parameterless, read-only health check with an output schema present, the description covers all an agent needs: what it returns, why to call it, and its caching behavior. The output schema handles return structure details, so the description does not need to repeat them.

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?

With zero parameters and 100% schema coverage, there are no parameter semantics to explain. The baseline for zero params is 4, and the description appropriately focuses on output and usage instead of inventing parameter details.

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 uses a specific verb ('Check live API & system health') and names the exact resources: all CryptoWhaleInsights data sources, MCP server, and OpenAPI spec. It clearly differentiates this health-status tool from metric-focused siblings like live_stats or platform_stats by emphasizing verdict and freshness rather than data values.

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

Usage Guidelines4/5

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

Explicitly states when to use the tool: 'verify the platform is live before making requests.' This gives an agent a clear decision rule. It does not name alternatives or say when not to use it, but for a zero-parameter health check this context is sufficient.

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

All whale-insights 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?