Dayze — Life Context

Create Pending Reply

create_pending_reply

Pending Replies (Inbox): save a reply the user owes someone, e.g. 'what to reply to X', 'I owe X a reply'. Use this, not log_event or a task. Optional draft (the reply text), summary (one line in your own words; never the email body, subject or sender), channel, category, received_at, and source { kind, thread_id, message_id } (ids only). Links the contact only when resolve_person finds exactly one (or pass person_id); otherwise the reply is saved unlinked and person_link says why. An unsent reply for the same thread or person comes back instead of a second one (created: false, deduplicated: true); update_existing: true replaces its draft and summary. Never sends anything. Requires API key or OAuth with context.write; share tokens cannot write. ($0.10; API key required)

Input Schema

TableJSON Schema

Name	Required	Description
`draft`	No	The reply text to send later, max 20,000 characters. Replaces the saved draft; empty or null clears. Alias: draft_message.
`source`	No	The email the reply answers, as ids only (e.g. a search_gmail id is a message_id). Never a subject, sender or text. On update, null clears it.
`channel`	No	Where to reply: whatsapp, email, sms, call, imessage, telegram, instagram, facebook, signal, linkedin, twitter, slack, teams, work_email, zoom, dayze, other. Default email when source is set, else other.
`summary`	No	One line (max 280) in your own words: what the reply is about. Never paste the email body, subject line or sender address.
`category`	No	Default personal.
`person_id`	No	An owned contact id; links that contact directly.
`request_id`	No	Client idempotency key (retries return original result).
`person_name`	Yes	Who the reply is owed to, as the user said it (e.g. "Ilana").
`received_at`	No	When they wrote (ISO date-time). Default now.
`draft_message`	No	Alias for draft.
`idempotency_key`	No	Alias for request_id.
`update_existing`	No	When an unsent reply for this thread or person exists, write draft/summary onto it instead of returning it unchanged.

Output Schema

TableJSON Schema

Name	Required	Description
`reply`	Yes	One reply the user owes (Inbox → Pending Replies). Dayze never sends it.
`account`	No	The Dayze account this data belongs to. With more than one Dayze connection, name it in the answer.
`app_url`	No
`created`	Yes	True when this call saved a new reply.
`message`	Yes
`updated`	Yes	True when an existing unsent reply was changed (update_existing).
`matched_on`	Yes	source_thread, source_message or person when deduplicated.
`provenance`	No	Which connector wrote the record and which connected Dayze account received it.
`person_link`	Yes	Whether a contact was linked. Linked only on one resolve_person match or an owned person_id.
`deduplicated`	Yes	True when an unsent reply for the same thread or person was returned instead of a new one.
`source_saved`	Yes	False when a source was given and could not be stored.
`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"
+}

Changed3 schema fields changedOct 1, 2026

addedOutput schema / properties / reply / properties / is_private

Added value: +{
+  "description": "Always true.",
+  "type": "boolean"
+}

addedOutput schema / properties / reply / properties / visibility

Added value: +{
+  "description": "Always private: Pending Replies have no sharing setting.",
+  "type": "string"
+}

changedOutput schema / properties / reply / required

Previous value: -[
-  "reply_id",
-  "person_name",
-  "person_id",
-  "channel",
-  "category",
-  "summary",
-  "draft",
-  "status",
-  "state",
-  "due",
-  "received_at",
-  "source"
-]New value: +[
+  "reply_id",
+  "person_name",
+  "person_id",
+  "channel",
+  "category",
+  "summary",
+  "draft",
+  "status",
+  "state",
+  "due",
+  "received_at",
+  "source",
+  "visibility",
+  "is_private"
+]

Changed1 schema field changedSep 30, 2026

addedOutput schema / properties / reply / properties / approved_at

Added value: +{
+  "description": "PHI-427: when the owner approved the draft and opened it in Gmail, or null. Dayze never sends; the Gmail sync closes the reply when the email goes out.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

Changed1 schema field changedSep 29, 2026
- addedInput schema / properties / draft_message
```
Added value: +{
+  "description": "Alias for draft.",
+  "type": "string"
+}
```

Changed2 schema fields changedSep 29, 2026

addedOutput schema / properties / reply / properties / due

Added value: +{
+  "description": "Owed now: pending, or snoozed with snooze_until passed. False while a snooze runs, and when sent or dismissed.",
+  "type": "boolean"
+}

changedOutput schema / properties / reply / required

Previous value: -[
-  "reply_id",
-  "person_name",
-  "person_id",
-  "channel",
-  "category",
-  "summary",
-  "draft",
-  "status",
-  "state",
-  "received_at",
-  "source"
-]New value: +[
+  "reply_id",
+  "person_name",
+  "person_id",
+  "channel",
+  "category",
+  "summary",
+  "draft",
+  "status",
+  "state",
+  "due",
+  "received_at",
+  "source"
+]

AddedSep 29, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations declare a non-destructive write; the description adds rich context beyond them: never sends anything, dedup returns created:false/deduplicated:true, linking fallback with person_link explaining why, auth requirements (context.write, share tokens cannot write), and cost ($0.10).

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: purpose first, then routing, then optional fields, dedup, auth and cost. Every sentence carries operational information, though the parenthetical field list makes it somewhat packed.

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 12-param mutation tool with an output schema and annotations, the description covers the write semantics, dedup, linking, auth, and cost. An agent has everything needed to call it correctly without guessing.

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 100%, so the baseline is 3, but the description adds meaning by tying parameters to behavior: person_id bypasses resolve_person linking, update_existing mutates an existing unsent reply, and summary must never contain the email body/subject/sender.

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?

States a specific verb+resource ('save a reply the user owes someone') with concrete examples ('what to reply to X', 'I owe X a reply'). Explicitly distinguishes itself from log_event and task, so an agent can route correctly 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 Guidelines5/5

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

Explicit 'Use this, not log_event or a task' names the alternatives and the condition that selects this tool. It further routes on dedup ('update_existing: true replaces its draft and summary') and linking ('only when resolve_person finds exactly one').

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.