SetLuca

Official

by setluca

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

Run a deep-dive analytics investigation

luca_analytics_deep_dive

Read-onlyIdempotent

Answer a specific business question by combining all seven analytics reads in one call, returning funnel, revenue, ROI, forecast, call, ghosted-lead and trust data side by side.

Instructions

Answer a specific business question by composing all seven analytics reads in one call: pipeline funnel, revenue and ROI, response-speed impact, a point-in-time revenue forecast, call intelligence (show/close rates), ghosted-lead recovery, and coach trust/auto-send status. Use it when the coach asks a specific question that needs several of these numbers side by side, rather than the fixed weekly report. Example: call with {question: "why did close rate drop this month?", period: "this_month"}.

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": "luca_analytics_deep_dive"
  }
}

Input Schema

Name	Required	Description
`period`	No	Period for the period-scoped reads (funnel, revenue, speedImpact, callIntelligence, ghostedLeads, trustScore). Forecast ignores this — it is always point-in-time. Defaults to this_month.
`question`	No	Optional. The coach's question behind this investigation, e.g. 'why did close rate drop this month?'. Not sent to any API; it only records what the coach asked.
`workspaceId`	No	Optional Luca workspace id override.
`workspaceSlug`	No	Optional Luca workspace slug override.

Output Schema

Name	Required	Description	Default
`result`	Yes
`provenance`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv0.4.2Nov 11, 2026

addedOutput schema / properties / result / properties / revenue / properties / wonDeals

Added value: +{
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}

addedOutput schema / properties / result / properties / trustScore / properties / autoSendReplyRate

Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

addedOutput schema / properties / result / properties / trustScore / properties / reviewedEditDistanceP50

Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

addedOutput schema / properties / result / properties / trustScore / properties / uneditedShare

Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

First observedv0.4.0Oct 21, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered; the description adds that this is a composite fan-out across seven reads, that period scoping applies to six while the forecast stays point-in-time, and that the question field is recorded but never sent to an API. It stops short of saying whether all seven reads always execute (cost/latency implications for a heavy call), which is the remaining gap.

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 purpose and the seven composed reads are front-loaded in the first sentence, with the usage rule and example following. The enumeration is long but each item earns its place by telling the agent what data will come back; there is no filler.

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, annotations carrying the safety profile, and fully documented parameters, the description only needs to establish composition scope and selection guidance, which it does. The one omission is whether all seven reads run unconditionally or are gated by the question, which affects expected latency and result shape.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so period enums, the forecast-ignores-period behavior, and the 'not sent to any API' nature of question are already documented in the schema. The description echoes the question/period example call but adds no syntax or constraints beyond that, so the baseline of 3 applies.

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 outcome ('answer a specific business question by composing all seven analytics reads in one call') and enumerates exactly which reads are bundled: funnel, revenue/ROI, speed impact, forecast, call intelligence, ghosted leads, and trust score. This lets an agent distinguish it from the individual sibling reads such as luca_analytics_funnel or luca_analytics_revenue without opening their schemas.

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?

It explicitly gives the condition for use ('when the coach asks a specific question that needs several of these numbers side by side') and an exclusion ('rather than the fixed weekly report'), plus a concrete example call. An agent can decide between this composite tool and the single-metric reads from the text alone.

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

Deploy Server