Dayze — Life Context

Log Food (diary write)

log_food

MUTATES the authenticated user Food Diary and calendar. Use when they ate or drank — do not store this as a chat memory. Supports dish_items for multiple named dishes with optional price and rating. Example: “I had Mee Pok for late lunch with my parents” → log_food({ what: "Mee Pok", kind: "meal", meal_period: "late lunch", with: ["my parents"] }). Optional: calories (user-stated kilocalories), place/merchant, amount, consumed_at (ISO). Explicit calories override the automatic heuristic. Resolves with/Mum/Dad via person aliases; unknown names do not fail the food write. Tags companions on the mirrored event. Rebuilds life_state. Requires API key or OAuth with scope context. Share tokens cannot write. ($0.10; API key required)

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	No
`what`	Yes	What they ate or drank (required). Example: Mee Pok
`with`	No	Companion names, aliases, ids, or group tokens. "my parents" / Mum / Dad resolve via aliases; "family" expands to CRM rows with family relationship labels
`notes`	No
`place`	No	Venue or location
`amount`	No	Price if mentioned
`paid_by`	No	Who paid (name or alias)
`calories`	No	Kilocalories explicitly stated by the user; overrides the automatic heuristic and is stored with user provenance
`currency`	No	ISO currency, e.g. SGD
`merchant`	No	Restaurant, stall, or shop
`dish_items`	No	Ordered dishes in this entry. Each requires name; price and rating are optional.
`person_ids`	No	Owned person UUIDs to tag (user-scoped)
`request_id`	No	Client idempotency key (retries return original result).
`consumed_at`	No	ISO instant; wins over meal_period
`meal_period`	No	Spoken period when consumed_at is omitted, e.g. "late lunch"
`people_names`	No	Alias for with
`idempotency_key`	No	Alias for request_id.

Output Schema

TableJSON Schema

Name	Required	Description
`account`	No	The Dayze account this data belongs to. With more than one Dayze connection, name it in the answer.
`food_id`	Yes
`message`	Yes
`event_id`	Yes
`food_log`	Yes	Saved Food Diary row.
`provenance`	No	Which connector wrote the record and which connected Dayze account received it.
`people_tagged`	Yes
`unresolved_people`	Yes
`life_state_rebuilt`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 3, 2026

addedOutput schema / properties / account

Added value: +{
+  "additionalProperties": false,
+  "description": "The Dayze account this data belongs to. With more than one Dayze connection, name it in the answer.",
+  "properties": {
+    "display_name": {
+      "description": "Account display name.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "handle": {
+      "description": "Account handle, e.g. @goh.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "note": {
+      "description": "How to disclose the account to the user.",
+      "type": "string"
+    },
+    "qa_fixture": {
+      "description": "True for a known QA test account: its records are fixture data, not a real life.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "handle",
+    "display_name",
+    "qa_fixture",
+    "note"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / provenance

Added value: +{
+  "additionalProperties": false,
+  "description": "Which connector wrote the record and which connected Dayze account received it.",
+  "properties": {
+    "account": {
+      "additionalProperties": false,
+      "description": "The Dayze account this data belongs to. With more than one Dayze connection, name it in the answer.",
+      "properties": {
+        "display_name": {
+          "description": "Account display name.",
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "handle": {
+          "description": "Account handle, e.g. @goh.",
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "note": {
+          "description": "How to disclose the account to the user.",
+          "type": "string"
+        },
+        "qa_fixture": {
+          "description": "True for a known QA test account: its records are fixture data, not a real life.",
+          "type": "boolean"
+        }
+      },
+      "required": [
+        "handle",
+        "display_name",
+        "qa_fixture",
+        "note"
+      ],
+      "type": "object"
+    },
+    "channel": {
+      "description": "Always mcp_connector.",
+      "type": "string"
+    },
+    "connector": {
+      "additionalProperties": false,
+      "properties": {
+        "kind": {
+          "description": "oauth or api_key.",
+          "type": "string"
+        },
+        "name": {
+          "description": "The connected app or API-key label shown to the account owner.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "kind",
+        "name"
+      ],
+      "type": "object"
+    },
+    "source": {
+      "description": "chatgpt for ChatGPT OAuth writes; mcp for another OAuth app or API key.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "source",
+    "channel",
+    "connector",
+    "account"
+  ],
+  "type": "object"
+}

Changed1 schema field changedSep 26, 2026

addedInput schema / properties / dish_items

Added value: +{
+  "description": "Ordered dishes in this entry. Each requires name; price and rating are optional.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "name": {
+        "type": "string"
+      },
+      "price": {
+        "minimum": 0,
+        "type": "number"
+      },
+      "rating": {
+        "maximum": 5,
+        "minimum": 1,
+        "type": "number"
+      }
+    },
+    "required": [
+      "name"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Changed1 schema field changedSep 26, 2026

addedInput schema / properties / calories

Added value: +{
+  "description": "Kilocalories explicitly stated by the user; overrides the automatic heuristic and is stored with user provenance",
+  "maximum": 10000,
+  "minimum": 0,
+  "type": "number"
+}

Changed1 schema field changedSep 24, 2026

changedInput schema / properties / consumed_at / description

Previous value: -"ISO 8601 datetime; wins over meal_period"New value: +"ISO instant; wins over meal_period"

Changed2 schema fields changedSep 4, 2026

addedInput schema / properties / idempotency_key

Added value: +{
+  "description": "Alias for request_id.",
+  "type": "string"
+}

addedInput schema / properties / request_id

Added value: +{
+  "description": "Client idempotency key (retries return original result).",
+  "type": "string"
+}

Changed1 schema field changedAug 31, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "event_id": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "food_id": {
+      "type": "string"
+    },
+    "food_log": {
+      "additionalProperties": true,
+      "description": "Saved Food Diary row.",
+      "type": "object"
+    },
+    "life_state_rebuilt": {
+      "type": "boolean"
+    },
+    "message": {
+      "type": "string"
+    },
+    "people_tagged": {
+      "items": {
+        "additionalProperties": true,
+        "description": "A Dayze person or contact record.",
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "unresolved_people": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "food_id",
+    "event_id",
+    "people_tagged",
+    "unresolved_people",
+    "food_log",
+    "message",
+    "life_state_rebuilt"
+  ],
+  "type": "object"
+}

Changed1 schema field changedAug 31, 2026

changedInput schema / properties / with / description

Previous value: -"Companion names, aliases, or ids. \"my parents\" / Mum / Dad resolve via aliases"New value: +"Companion names, aliases, ids, or group tokens. \"my parents\" / Mum / Dad resolve via aliases; \"family\" expands to CRM rows with family relationship labels"

AddedAug 29, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only cover readOnly/destructive/openWorld, but the description adds substantial behavioral context: it mirrors a calendar event, tags companions on that event, rebuilds life_state, resolves aliases (with/Mum/Dad), tolerates unknown names without failing, and discloses write auth requirements and a $0.10 cost. This is well beyond what the annotations convey.

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 mutation and usage cue are front-loaded, and the worked example plus optional-parameter summary are useful rather than padding. It is dense with parenthetical auth and pricing details at the tail, which slightly dilutes scannability but almost every sentence carries information.

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 17-parameter mutation tool with an output schema, the description covers the essentials an agent needs: trigger, exclusions, side effects (calendar mirror, life_state rebuild, companion tagging), alias resolution behavior, auth model, and cost. Return values are legitimately left to the output schema.

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 88%, so the schema already documents most parameters (what, with, calories, consumed_at, dish_items, etc.). The description largely restates this (calories override the heuristic, dish_items with price/rating, consumed_at wins over meal_period), so it adds only marginal value over the structured schema — the baseline 3 for high coverage is appropriate.

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 leads with a specific verb+resource+'MUTATES the authenticated user Food Diary and calendar', and immediately distinguishes itself from sibling tools by saying 'do not store this as a chat memory'. An agent can tell it apart from update_food, log_expense, and log_moment without opening a schema.

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?

It states the trigger condition ('Use when they ate or drank') and an explicit exclusion ('do not store this as a chat memory'), plus auth constraints ('Requires API key or OAuth'; 'Share tokens cannot write'). It stops short of naming the specific sibling alternatives for adjacent cases (e.g. log_expense for costs), so it lands just below full routing guidance.

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

All Dayze — Life Context 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.