Skip to main content
Glama
gohluke

Dayze MCP

by gohluke
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Semantic Life Search

search
Read-only

Search a user's life graph for events, food, money, and people, routing common queries like 'what did I eat yesterday?' deterministically and using semantic search otherwise.

Instructions

Search the authenticated user life graph. Deterministic routing first: food + relative dates (e.g. "what did I eat yesterday?"); timeline/current-context; money+person; who-is → resolve_person. Otherwise semantic/keyword search. Event hits include event_date and food_id when mirrored from Food Diary. Browser-history titles are excluded. Credential/secret spans are redacted. Requires OAuth or a supported scoped credential. ($0.15; API key required)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYes
intentNo
resultsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.28.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / anyOf
      Added value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "limit": {
+        "default": 10,
+        "description": "Max results 1–50",
+        "type": "number"
+      },
+      "q": {
+        "description": "Alias for query.",
+        "type": "string"
+      },
+      "query": {
+        "description": "Primary search query.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "query"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "limit": {
+        "default": 10,
+        "description": "Max results 1–50",
+        "type": "number"
+      },
+      "q": {
+        "description": "Alias for query.",
+        "type": "string"
+      },
+      "query": {
+        "description": "Primary search query.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "q"
+    ],
+    "type": "object"
+  }
+]
    • removedInput schema / properties
      Removed value: -{
-  "limit": {
-    "default": 10,
-    "description": "Max results 1–50",
-    "type": "number"
-  },
-  "q": {
-    "description": "Alias for query",
-    "type": "string"
-  },
-  "query": {
-    "description": "Search query (primary)",
-    "type": "string"
-  }
-}
    • removedInput schema / required
      Removed value: -[
-  "query"
-]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "intent": {
+      "type": "string"
+    },
+    "mode": {
+      "enum": [
+        "semantic",
+        "keyword",
+        "blended",
+        "structured"
+      ],
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "content": {
+            "type": "string"
+          },
+          "event_date": {
+            "type": "string"
+          },
+          "food_id": {
+            "type": "string"
+          },
+          "similarity": {
+            "type": "number"
+          },
+          "source_id": {
+            "type": "string"
+          },
+          "source_type": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "source_type",
+          "source_id",
+          "title",
+          "content",
+          "similarity"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "mode",
+    "results"
+  ],
+  "type": "object"
+}
  2. First observedv1.6.2

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already mark the tool read-only and non-destructive, and the description goes further by disclosing deterministic routing, event-hit enrichment with event_date and food_id, exclusion of browser-history titles, redaction of credential/secret spans, auth requirements, cost, and API-key necessity. This is rich behavioral context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every clause earns its place: scope, routing, output hints, exclusions, redaction, auth, and cost are packed into five dense sentences. The core action is front-loaded before the conditional routing details.

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 broad search tool with an output schema, the description provides all necessary operational context: what it searches, how queries are routed, what fields event hits include, what is excluded/redacted, and what credentials are required. No important calling decision is left unresolved.

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 context reports zero parameters and 100% schema description coverage, so the baseline is 4; nothing is left unclear. The description's example query supports the query semantics, and the schema itself already documents q, query, and limit.

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 opens with a specific verb and resource: 'Search the authenticated user life graph.' It then details deterministic routing categories and a fallback, which clearly distinguishes this broad life-graph search from siblings like search_gmail, search_photos, and search_transactions.

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 offers concrete routing guidance: food plus relative dates, timeline/current-context, money+person, and who-is, explicitly delegating who-is to resolve_person. It does not, however, explicitly state when to prefer targeted sibling search tools over this generic search, so it lacks formal when-not-to-use exclusions.

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