whale-insights

analyst_monthly_performance

Read-onlyIdempotent

Monthly performance summary for all analysts (last 6 months) — Returns win_rate, avg_return, and total_signals per analyst per calendar month for exactly the last 6 calendar months (current month + 5 prior full months, enforced with DATE_TRUNC('month') boundaries — never more than 6 month buckets). All 10 canonical analysts (chain_hawk, whale_watch, alpha_scout, defi_pulse, quant_edge, rate_hawk, flow_tracer, unlock_guard, sentiment_edge, narrative_pulse) are always present in the response with an empty array [] when they have no signals in the window. Data is computed directly from the signal_history PostgreSQL table — no separate snapshot table required. winRate is a fraction (0–1, e.g. 0.71 = 71%) and is null when fewer than 5 resolved signals exist for that month. avgReturn is in percentage points (e.g. 12.3 = +12.3% average return) and is null when no resolved+priced signals exist for that month. Useful for AI agents answering 'How did WhaleWatch perform in May?' or 'Who was the best analyst last month?'

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description
`months`	No	Look-back window in months (always 6).
`updatedAt`	No
`attribution`	No
`performance`	No	Keys are analyst slugs (chain_hawk, whale_watch, …); values are arrays of monthly performance objects ordered newest-first.

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"
+    },
+    "months": {
+      "description": "Look-back window in months (always 6).",
+      "type": "integer"
+    },
+    "performance": {
+      "additionalProperties": {
+        "items": {
+          "properties": {
+            "avgReturn": {
+              "description": "Average return in pct-points. Null when no resolved+priced signals.",
+              "nullable": true,
+              "type": "number"
+            },
+            "losses": {
+              "type": "integer"
+            },
+            "month": {
+              "description": "Calendar month in YYYY-MM format, e.g. '2026-05'.",
+              "type": "string"
+            },
+            "resolved": {
+              "description": "Signals with a win or loss outcome in this month (neutral excluded from denominator, consistent with analyst stats logic).",
+              "type": "integer"
+            },
+            "totalSignals": {
+              "description": "All signals attributed to this analyst in this month (resolved + unresolved).",
+              "type": "integer"
+            },
+            "winRate": {
+              "description": "Fraction 0–1. Null when resolved < 5.",
+              "nullable": true,
+              "type": "number"
+            },
+            "wins": {
+              "type": "integer"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "description": "Keys are analyst slugs (chain_hawk, whale_watch, …); values are arrays of monthly performance objects ordered newest-first.",
+      "type": "object"
+    },
+    "updatedAt": {
+      "format": "date-time",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedJun 26, 2026

TDQS

A4.6/5.0

Behavior5/5

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

The description adds substantial behavior beyond the annotations: exact calendar-month boundary enforcement via DATE_TRUNC, the guarantee that all 10 analysts appear even with empty arrays, direct querying of signal_history, and null conditions for winRate and avgReturn. This is rich operational context that annotations alone do not provide.

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 dense and front-loaded with the core purpose, and nearly every detail earns its place. It is slightly verbose due to the parenthetical DATE_TRUNC explanation, the repeated 'never more than 6 month buckets' guarantee, and the full analyst list, but it remains readable and well organized.

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 zero-parameter read-only tool with an output schema and complete annotations, the description covers invocation context, edge cases (few signals => null winRate; no resolved+priced signals => null avgReturn), the deterministic analyst set, and example user queries. Nothing needed to select or interpret this tool 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?

The tool accepts zero parameters and schema description coverage is 100%, so there are no parameter semantics to document. The baseline for zero-parameter tools is 4; the description appropriately invests in return-value semantics instead.

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 ('Returns'), a specific resource ('performance summary for all analysts'), and a precise scope ('exactly the last 6 calendar months'). It also distinguishes itself from sibling tools like analyst_daily_summary by explicitly describing monthly granularity and enumerating the 10 canonical analysts covered.

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?

The description gives concrete query examples ('How did WhaleWatch perform in May?' or 'Who was the best analyst last month?') and clearly defines the 6-month window, making when to use it clear. It does not explicitly name alternatives or state when not to use this tool, so it falls just 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?