whale-insights

analysts_top

Read-onlyIdempotent

Get the highest win-rate analyst right now — one analyst with win rate, avg return, last 3 signals (min 5 resolved trades required) — Returns the single analyst with the highest win rate among those with at least 5 resolved signals, plus their last 3 recent signals (using the free 7-day window). Useful for AI agents that want to surface the best-performing signal source without iterating over all 10 analysts. Returns { analyst: null } when no analyst yet has 5+ resolved signals. Analyst IDs map to: chain_hawk=ChainHawk (BTC), whale_watch=WhaleWatch (multi-chain), alpha_scout=AlphaScout (emerging tokens), defi_pulse=DeFiPulse (DeFi/stables), quant_edge=QuantEdge (risk/convergence). winRate is a fraction (0.71 = 71%); avgReturn is percentage points (12.3 = +12.3%). Cached ~10min.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "analysts_top"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`analyst`	No	The analyst with the highest win rate (min 5 resolved signals). Null if no analyst qualifies yet.
`updatedAt`	No
`attribution`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "analyst": {
+      "description": "The analyst with the highest win rate (min 5 resolved signals). Null if no analyst qualifies yet.",
+      "nullable": true,
+      "properties": {
+        "avgReturn": {
+          "description": "Average return in percentage points.",
+          "type": "number"
+        },
+        "bio": {
+          "type": "string"
+        },
+        "id": {
+          "type": "string"
+        },
+        "lastSignalAt": {
+          "format": "date-time",
+          "nullable": true,
+          "type": "string"
+        },
+        "name": {
+          "type": "string"
+        },
+        "recentSignals": {
+          "items": {
+            "description": "Last 3 signals attributed to this analyst (free 7-day window)",
+            "properties": {
+              "createdAt": {
+                "format": "date-time",
+                "type": "string"
+              },
+              "outcome": {
+                "nullable": true,
+                "type": "string"
+              },
+              "returnPct": {
+                "nullable": true,
+                "type": "number"
+              },
+              "tokens": {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              "typeLabel": {
+                "type": "string"
+              }
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "resolvedSignals": {
+          "type": "number"
+        },
+        "specialization": {
+          "type": "string"
+        },
+        "totalSignals": {
+          "type": "number"
+        },
+        "winRate": {
+          "description": "Fraction (0–1). Multiply by 100 for %.",
+          "type": "number"
+        }
+      },
+      "type": "object"
+    },
+    "attribution": {
+      "$ref": "#/components/schemas/Attribution"
+    },
+    "updatedAt": {
+      "format": "date-time",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedJun 19, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the read-only, idempotent annotations by disclosing the null-return edge case, the 5-signal minimum, the 7-day window, the ~10-minute cache, and units for winRate and avgReturn. No contradiction with annotations exists.

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?

Core behavior is front-loaded and most sentences contribute useful context such as caching, units, ID mapping, and null behavior. However, the second sentence largely repeats information already given in the first sentence, preventing a perfect score.

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 no-parameter read-only tool with an output schema, the description covers selection criteria, edge cases, units, analyst ID mappings, and freshness. Nothing material is missing for an agent to invoke and interpret this tool correctly.

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?

The tool has zero parameters, so schema coverage is trivially high and there is no parameter syntax for the description to clarify. Under the rubric, a 0-parameter tool gets a baseline of 4.

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?

Description clearly states a specific function: return the single analyst with the highest win rate among those with 5+ resolved signals, including win rate, avg return, and last 3 signals. It also distinguishes its purpose from siblings by noting it exists to avoid iterating over all 10 analysts.

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?

Provides a clear use case: surface the best-performing signal source without iterating over all analysts. However, it does not explicitly name alternative tools or state when not to use this tool, so it stops short of full exclusion guidance.

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?