Dayze — Life Context

Link Entities

link_entities

Link Trip→Stay→Place / Event→Person (graph, not prose). link_type accepts documented aliases (e.g. participant → event_person); unknown values error instead of silently becoming "other". Pass status=confirmed|rejected to record a human decision on an existing (often inferred) edge. status=confirmed on a link that does not exist yet creates it, as a call without status does (explicit, confidence 1). status=rejected on a link that does not exist errors and saves nothing: there is nothing to reject. ($0.10; API key required)

Input Schema

TableJSON Schema

Name	Required	Description
`notes`	No
`to_id`	Yes
`source`	No	Provenance tag, e.g. manual, inferred:name_match:title.
`status`	No	confirmed: confirm an existing edge (usually an inferred one: +confirmed, confidence 1), or create the edge if it does not exist yet, as a call without status does. rejected: tombstone an existing edge (+rejected, confidence 0). A rejected edge is not a relationship: the event's people, timelines, get_interactions and every other read leave it out. It is kept so automated writers never recreate it; linking the same pair again without status replaces it. Errors and saves nothing when the edge does not exist.
`from_id`	Yes
`to_type`	Yes
`from_type`	Yes
`link_type`	No	trip_stay \| trip_flight \| stay_place \| event_place \| event_person \| transaction_trip \| event_event \| other. Aliases: participant/participants/attendee/attendees → event_person.
`confidence`	No	0-1. Defaults to 1 for explicit links. 0 means rejected: every read leaves the edge out.
`request_id`	No	Client idempotency key (retries return original result).
`idempotency_key`	No	Alias for request_id.

Output Schema

TableJSON Schema

Name	Required	Description
`link`	No	The stored life_entity_links row.
`linked`	No
`account`	No	The Dayze account this data belongs to. With more than one Dayze connection, name it in the answer.
`message`	No
`provenance`	No	Which connector wrote the record and which connected Dayze account received it.
`confirmation`	No	Derived from the link source and confidence. explicit: a direct write; pending: an inferred guess nobody has confirmed; confirmed: a guess a person confirmed; rejected: a person rejected it (source ends in +rejected, or confidence 0). A rejected link is kept only so it is never proposed again; it is not a relationship.

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"
+}

Changed4 schema fields changedSep 29, 2026

changedInput schema / properties / confidence / description

Previous value: -"0-1. Defaults to 1 for explicit links."New value: +"0-1. Defaults to 1 for explicit links. 0 means rejected: every read leaves the edge out."

changedInput schema / properties / status / description

Previous value: -"confirmed: confirm an existing edge (usually an inferred one: +confirmed, confidence 1), or create the edge if it does not exist yet, as a call without status does. rejected: tombstone an existing edge (+rejected, confidence 0, kept so automated writers never recreate it); errors and saves nothing when the edge does not exist."New value: +"confirmed: confirm an existing edge (usually an inferred one: +confirmed, confidence 1), or create the edge if it does not exist yet, as a call without status does. rejected: tombstone an existing edge (+rejected, confidence 0). A rejected edge is not a relationship: the event's people, timelines, get_interactions and every other read leave it out. It is kept so automated writers never recreate it; linking the same pair again without status replaces it. Errors and saves nothing when the edge does not exist."

addedOutput schema / properties / confirmation

Added value: +{
+  "description": "Derived from the link source and confidence. explicit: a direct write; pending: an inferred guess nobody has confirmed; confirmed: a guess a person confirmed; rejected: a person rejected it (source ends in +rejected, or confidence 0). A rejected link is kept only so it is never proposed again; it is not a relationship.",
+  "enum": [
+    "explicit",
+    "pending",
+    "confirmed",
+    "rejected"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / link / description

Added value: +"The stored life_entity_links row."

Changed1 schema field changedSep 28, 2026

changedInput schema / properties / status / description

Previous value: -"Confirm or reject an existing edge (usually an inferred one). Requires the edge to already exist."New value: +"confirmed: confirm an existing edge (usually an inferred one: +confirmed, confidence 1), or create the edge if it does not exist yet, as a call without status does. rejected: tombstone an existing edge (+rejected, confidence 0, kept so automated writers never recreate it); errors and saves nothing when the edge does not exist."

Changed4 schema fields changedSep 25, 2026

addedInput schema / properties / confidence

Added value: +{
+  "description": "0-1. Defaults to 1 for explicit links.",
+  "type": "number"
+}

addedInput schema / properties / link_type / description

Added value: +"trip_stay | trip_flight | stay_place | event_place | event_person | transaction_trip | event_event | other. Aliases: participant/participants/attendee/attendees → event_person."

addedInput schema / properties / source

Added value: +{
+  "description": "Provenance tag, e.g. manual, inferred:name_match:title.",
+  "type": "string"
+}

addedInput schema / properties / status

Added value: +{
+  "description": "Confirm or reject an existing edge (usually an inferred one). Requires the edge to already exist.",
+  "enum": [
+    "confirmed",
+    "rejected"
+  ],
+  "type": "string"
+}

AddedSep 4, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond the annotations: explains that unknown link_type values error rather than silently degrading, that confirmed on a non-existent edge creates it (confidence 1), and that rejected on a non-existent edge errors and saves nothing. The read-exclusion behavior of rejected edges ('every other read leaves it out') is exactly the kind of context an agent cannot get from the schema.

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?

Dense but front-loaded, leading with the graph-vs-prose framing and alias behavior before the status rules. Slightly repetitive around the 'as a call without status does' phrasing and the cost/key parenthetical tacked on the end.

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?

For an 11-parameter mutation tool with an output schema present, the description covers the risky/ambiguous behaviors (aliases, status transitions, rejection tombstoning, idempotency implied). The $0.10 cost and API-key note is useful, though details like confidence default handling could be firmer.

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?

Schema coverage is only 55%, but the description compensates for the most consequential parameters: link_type alias resolution and error behavior, and status create-vs-reject semantics. It does not add much for from_type/to_type/from_id/to_id, which is a minor residual gap.

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+resource ('Link ... graph, not prose') and gives concrete example paths (Trip→Stay→Place, Event→Person). The parenthetical '(graph, not prose)' distinguishes it from log_event/log_interaction-style prose writers among the siblings.

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 status semantics give clear 'use this when' guidance: confirmed to record a human decision on an existing/inferred edge, rejected to tombstone one. It does not point at sibling alternatives such as get_entity_links or link_people, so routing to this tool vs related ones is left implicit.

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.