Skip to main content
Glama
Sign In
SetLuca

SetLuca

Official
by setluca
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Triage the review queue

luca_triage_inbox
Read-onlyIdempotent

Reads the coach's prioritized reply queue, returning pending drafts with lead context and explanations for top items so you can review what needs attention without sending messages.

Instructions

Return the coach's prioritized reply queue: pending drafts with lead context and, for the top items, why Luca drafted what it drafted. With a redacted OAuth grant, lead names and draft text can be blanked; describe them as unavailable rather than empty. Start a review session here: it reads the queue and sends nothing. Example: call with { explainTop: 3 } to get the queue plus explanations for the three most urgent drafts.

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_triage_inbox"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax queue items to return (default 20).
explainTopNoHow many of the top items to attach a full explanation to (default 3).
workspaceIdNoOptional Luca workspace id override.
workspaceSlugNoOptional Luca workspace slug override.

Output Schema

NameRequiredDescriptionDefault
resultYes
provenanceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.2
    • changedOutput schema / properties / result / properties / queue / x-luca-redacted-fields
      Previous value: -[
-  "items[].criticIssues",
-  "items[].draftBody",
-  "items[].draftContent",
-  "items[].draftParts",
-  "items[].leadDisplayName",
-  "items[].media",
-  "items[].mediaContext",
-  "items[].objectionVariants",
-  "items[].qualification",
-  "items[].safetyFindings",
-  "items[].signals"
-]New value: +[
+  "items[].criticIssues",
+  "items[].draftBody",
+  "items[].draftContent",
+  "items[].draftParts",
+  "items[].lastInboundMessages",
+  "items[].leadDisplayName",
+  "items[].leadProfilePhotoUrl",
+  "items[].media",
+  "items[].mediaContext",
+  "items[].objectionVariants",
+  "items[].qualification",
+  "items[].safetyFindings",
+  "items[].sentBody",
+  "items[].signals"
+]
  2. Changed3 schema fields changedv0.4.1
    • changedOutput schema / properties / result / properties / explanations / additionalProperties / anyOf
      Previous value: -[
-  {
-    "anyOf": [
-      {
-        "additionalProperties": true,
-        "properties": {
-          "confidence": {
-            "type": "number"
-          },
-          "createdAt": {
-            "type": "string"
-          },
-          "criticIssues": {},
-          "draftBody": {
-            "type": "string"
-          },
-          "id": {
-            "type": "string"
-          },
-          "leadId": {
-            "type": "string"
-          },
-          "qualification": {},
-          "status": {
-            "type": "string"
-          },
-          "voiceMatchScore": {
-            "type": "number"
-          }
-        },
-        "type": "object"
-      },
-      {
-        "additionalProperties": true,
-        "properties": {
-          "id": {
-            "type": "string"
-          },
-          "leadId": {
-            "type": "string"
-          },
-          "reason": {
-            "type": "string"
-          },
-          "status": {
-            "type": "string"
-          }
-        },
-        "type": "object"
-      }
-    ],
-    "x-luca-redacted-fields": [
-      "criticIssues",
-      "draftBody",
-      "qualification"
-    ]
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "explainError": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "explainError"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "anyOf": [
+      {
+        "additionalProperties": true,
+        "properties": {
+          "confidence": {
+            "type": "number"
+          },
+          "createdAt": {
+            "type": "string"
+          },
+          "criticIssues": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "number"
+              },
+              {
+                "type": "boolean"
+              },
+              {
+                "type": "object"
+              },
+              {
+                "type": "array"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "draftBody": {
+            "type": "string"
+          },
+          "id": {
+            "type": "string"
+          },
+          "leadId": {
+            "type": "string"
+          },
+          "qualification": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "number"
+              },
+              {
+                "type": "boolean"
+              },
+              {
+                "type": "object"
+              },
+              {
+                "type": "array"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "status": {
+            "type": "string"
+          },
+          "voiceMatchScore": {
+            "type": "number"
+          }
+        },
+        "type": "object"
+      },
+      {
+        "additionalProperties": true,
+        "properties": {
+          "id": {
+            "type": "string"
+          },
+          "leadId": {
+            "type": "string"
+          },
+          "reason": {
+            "type": "string"
+          },
+          "status": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      }
+    ],
+    "x-luca-redacted-fields": [
+      "criticIssues",
+      "draftBody",
+      "qualification"
+    ]
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "explainError": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "explainError"
+    ],
+    "type": "object"
+  }
+]
    • addedOutput schema / properties / result / properties / queue / properties / asOf
      Added value: +{
+  "type": "string"
+}
    • changedOutput schema / properties / result / properties / queue / x-luca-redacted-fields
      Previous value: -[
-  "items[].criticIssues",
-  "items[].draftBody",
-  "items[].draftParts",
-  "items[].leadDisplayName",
-  "items[].media",
-  "items[].mediaContext",
-  "items[].objectionVariants",
-  "items[].qualification",
-  "items[].safetyFindings",
-  "items[].signals"
-]New value: +[
+  "items[].criticIssues",
+  "items[].draftBody",
+  "items[].draftContent",
+  "items[].draftParts",
+  "items[].leadDisplayName",
+  "items[].media",
+  "items[].mediaContext",
+  "items[].objectionVariants",
+  "items[].qualification",
+  "items[].safetyFindings",
+  "items[].signals"
+]
  3. First observedv0.4.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, yet the description adds real value: the redacted-OAuth-grant caveat telling the agent to describe blanked lead names and draft text as 'unavailable rather than empty.' That is a disclosure an agent could not get from structured fields. The 'sends nothing' line is largely redundant with readOnlyHint.

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?

Purpose is front-loaded in the first sentence, followed by the redaction caveat, the session-entry note, and a worked example — a sensible order. All four sentences carry information, though 'it reads the queue and sends nothing' partly repeats the readOnly annotation.

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, return-shape detail is unnecessary and the description still sketches the payload usefully. It covers the key edge case (redacted grants) for a read-only, four-optional-parameter tool. The only gap is routing among near-identical queue siblings.

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 coverage is 100%, so the schema already documents limit, explainTop, workspaceId, and workspaceSlug with defaults. The worked example { explainTop: 3 } and the phrase 'for the top items, why Luca drafted what it drafted' reinforce explainTop's meaning, but nothing new is said about the two workspace override parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete verb and resource: 'Return the coach's prioritized reply queue: pending drafts with lead context' plus inline explanations for top items. That is far more than the title restates. It does not explicitly contrast itself with the close sibling luca_review_queue_list, so an agent must infer which of the two is the entry point.

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

Usage Guidelines3/5

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

'Start a review session here' signals it is the entry point and the example call shows a concrete invocation. However, no alternative is named and no when-not condition is given, even though siblings like luca_review_queue_list and luca_review_queue_explain overlap in scope.

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

Deploy Server

Other Tools