Dayze — Life Context

Search Gmail (read-only)

search_gmail

Read-only

Search one of the authenticated user's connected Gmail inboxes (read-only). Reuses Integrations hub Gmail (service_connections provider=gmail). Optional account/email selects a mailbox when multiple are connected — call list_gmail_accounts first. Prefer Gmail operators: from:, subject:, is:unread, newer_than:7d, has:attachment. For clock-time constraints, pass after/before as account-local civil datetimes; the tool converts them to precise UTC instants. Returns id, subject, from, canonical date, account-local date_local, time_zone, and snippet only (no body), newest first (newest_first: true). For the latest / most recent email from someone, query from: alone, without quoted topic phrases (the newest reply often lacks them); a from: + topic search with no match from the last 7 days also searches the sender alone and marks those messages sender_only (see note). Follow up with read_gmail_message. Cannot send, archive, or delete. Never invent email contents. If Gmail is not connected, connect at /integrations. Requires mail.read on an API key or non-ChatGPT OAuth connection. ChatGPT profiles do not grant mail.read or list this tool. Share tokens cannot call this tool. ($0.10; API key required)

Input Schema

TableJSON Schema

Name	Required	Description
`q`	No	Alias for query
`after`	No	Exclusive lower bound as account-local YYYY-MM-DDTHH:mm, or an offset-aware ISO instant
`email`	No	Alias for account
`query`	Yes	Gmail search query, e.g. "is:unread newer_than:7d", "from:airline subject:itinerary", "receipt newer_than:30d"
`before`	No	Exclusive upper bound as account-local YYYY-MM-DDTHH:mm, or an offset-aware ISO instant
`account`	No	Mailbox email, connection id, or Google subject (from list_gmail_accounts)
`max_results`	No	Max messages to return (default 10, max 20)

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No	What the ranking means for a "latest email" answer.
`after`	No
`query`	Yes
`before`	No
`account`	No
`messages`	Yes
`time_zone`	Yes
`newest_first`	Yes	Messages are ranked newest first by received time.
`sender_check`	No	A from: + topic search with no recent match also searched the sender alone (one extra search).
`unavailable_count`	No	Matches whose details could not be loaded; one may be newer.
`result_size_estimate`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 28, 2026

addedOutput schema / properties / messages / items / properties / sender_only

Added value: +{
+  "description": "From the sender-only check: the sender's mail, missing some of the topic terms.",
+  "type": "boolean"
+}

addedOutput schema / properties / newest_first

Added value: +{
+  "description": "Messages are ranked newest first by received time.",
+  "type": "boolean"
+}

addedOutput schema / properties / note

Added value: +{
+  "description": "What the ranking means for a \"latest email\" answer.",
+  "type": "string"
+}

addedOutput schema / properties / sender_check

Added value: +{
+  "additionalProperties": false,
+  "description": "A from: + topic search with no recent match also searched the sender alone (one extra search).",
+  "properties": {
+    "added": {
+      "type": "number"
+    },
+    "failed": {
+      "type": "boolean"
+    },
+    "query": {
+      "type": "string"
+    },
+    "reason": {
+      "type": "string"
+    },
+    "window_days": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "query",
+    "reason",
+    "window_days",
+    "added",
+    "failed"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / unavailable_count

Added value: +{
+  "description": "Matches whose details could not be loaded; one may be newer.",
+  "type": "number"
+}

changedOutput schema / required

Previous value: -[
-  "query",
-  "result_size_estimate",
-  "messages",
-  "time_zone"
-]New value: +[
+  "query",
+  "result_size_estimate",
+  "newest_first",
+  "messages",
+  "time_zone"
+]

Changed9 schema fields changedSep 24, 2026

addedInput schema / properties / after

Added value: +{
+  "description": "Exclusive lower bound as account-local YYYY-MM-DDTHH:mm, or an offset-aware ISO instant",
+  "type": "string"
+}

addedInput schema / properties / before

Added value: +{
+  "description": "Exclusive upper bound as account-local YYYY-MM-DDTHH:mm, or an offset-aware ISO instant",
+  "type": "string"
+}

addedOutput schema / properties / after
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / before
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / messages / items / properties / date_local
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / messages / items / properties / time_zone
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / properties / messages / items / required

Previous value: -[
-  "id",
-  "subject",
-  "from",
-  "date",
-  "snippet"
-]New value: +[
+  "id",
+  "subject",
+  "from",
+  "date",
+  "date_local",
+  "time_zone",
+  "snippet"
+]

addedOutput schema / properties / time_zone
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / required

Previous value: -[
-  "query",
-  "result_size_estimate",
-  "messages"
-]New value: +[
+  "query",
+  "result_size_estimate",
+  "messages",
+  "time_zone"
+]

Changed4 schema fields changedSep 13, 2026

addedInput schema / properties / account

Added value: +{
+  "description": "Mailbox email, connection id, or Google subject (from list_gmail_accounts)",
+  "type": "string"
+}

addedInput schema / properties / email

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

addedOutput schema / properties / account

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / properties / messages / items / properties / date / type
```
Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
```

Changed1 schema field changedAug 31, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "messages": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "date": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "from": {
+            "type": "string"
+          },
+          "id": {
+            "type": "string"
+          },
+          "snippet": {
+            "type": "string"
+          },
+          "subject": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "subject",
+          "from",
+          "date",
+          "snippet"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "query": {
+      "type": "string"
+    },
+    "result_size_estimate": {
+      "type": [
+        "number",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "query",
+    "result_size_estimate",
+    "messages"
+  ],
+  "type": "object"
+}

AddedAug 29, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare read-only/non-destructive, but the description adds substantial context: only id/subject/from/date/date_local/time_zone/snippet are returned (no body), newest-first ordering, the sender_only fallback when a from:+topic search misses, auth requirements (mail.read on API key or non-ChatGPT OAuth), ChatGPT profiles not granting access, share tokens blocked, and connection setup at /integrations.

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?

Front-loaded with purpose and scoping, then constraints and behavior. Dense but every clause carries information; a few parenthetical asides (the $0.10 cost, the sender_only 'see note' cross-reference) make it longer than ideal, though nothing is truly filler.

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?

Given an output schema exists, return fields need not be explained yet it still summarizes them, and it covers auth, prerequisites, cost, and a behavioral edge case (sender-only fallback). Nothing an agent needs to invoke this correctly is missing.

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 real meaning beyond the schema: after/before are account-local civil datetimes converted to precise UTC instants (an execution behavior not visible in the schema), the account/email alias relationship, and practical query-construction guidance. It stops short of documenting max_results' 20 cap in prose, but that is already in the schema.

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 with scope ('search one of the authenticated user's connected Gmail inboxes, read-only'), and distinguishes itself from siblings by naming list_gmail_accounts, read_gmail_message, and the import_*_gmail tools it is not. An agent can route correctly without opening the 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?

Gives explicit when-to-use guidance (call list_gmail_accounts first when multiple mailboxes; follow up with read_gmail_message), operator preferences (from:, subject:, is:unread, newer_than:7d), and a specific alternative query pattern for the latest email from a sender. Also states exclusions: cannot send, archive, or delete.

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.