readNdraft IMAP MCP

Overview Schema Source Related Servers Discussions Admin

search_emails

Read-onlyIdempotent

Find email metadata across IMAP mailboxes by sender, subject, recipient, text, dates, read state, or attachment name, with optional paging and stable order.

Instructions

Search 1-500 metadata rows in stable mailbox order with optional paging.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`read`	No
`text`	No
`after`	No
`limit`	No
`before`	No
`cursor`	No
`fields`	No
`sender`	No
`starred`	No
`subject`	No
`targets`	Yes
`recipient`	No
`attachment_filename`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`order`	Yes
`errors`	Yes
`results`	Yes
`truncated`	Yes
`next_cursor`	Yes
`target_statuses`	Yes
`targets_pending`	Yes
`targets_searched`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.10.0Sep 13, 2026

addedOutput schema / $defs / SearchTargetStatusOutput

Added value: +{
+  "properties": {
+    "account_id": {
+      "title": "Account Id",
+      "type": "string"
+    },
+    "cursor": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "title": "Cursor"
+    },
+    "error": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "title": "Error"
+    },
+    "mailbox": {
+      "title": "Mailbox",
+      "type": "string"
+    },
+    "status": {
+      "enum": [
+        "complete",
+        "partial",
+        "error",
+        "pending"
+      ],
+      "title": "Status",
+      "type": "string"
+    }
+  },
+  "required": [
+    "account_id",
+    "mailbox",
+    "status",
+    "cursor",
+    "error"
+  ],
+  "title": "SearchTargetStatusOutput",
+  "type": "object"
+}

addedOutput schema / properties / target_statuses

Added value: +{
+  "items": {
+    "$ref": "#/$defs/SearchTargetStatusOutput"
+  },
+  "title": "Target Statuses",
+  "type": "array"
+}

changedOutput schema / required

Previous value: -[
-  "results",
-  "errors",
-  "next_cursor",
-  "truncated",
-  "order",
-  "targets_searched",
-  "targets_pending"
-]New value: +[
+  "results",
+  "errors",
+  "next_cursor",
+  "truncated",
+  "order",
+  "targets_searched",
+  "targets_pending",
+  "target_statuses"
+]

Changed5 schema fields changedv0.9.0Aug 30, 2026

addedInput schema / $defs

Added value: +{
+  "SearchTargetInput": {
+    "properties": {
+      "account_id": {
+        "title": "Account Id",
+        "type": "string"
+      },
+      "mailbox": {
+        "title": "Mailbox",
+        "type": "string"
+      }
+    },
+    "required": [
+      "account_id",
+      "mailbox"
+    ],
+    "title": "SearchTargetInput",
+    "type": "object"
+  }
+}

removedInput schema / properties / accounts

Removed value: -{
-  "items": {
-    "type": "string"
-  },
-  "title": "Accounts",
-  "type": "array"
-}

removedInput schema / properties / mailboxes

Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "title": "Mailboxes"
-}

addedInput schema / properties / targets

Added value: +{
+  "items": {
+    "$ref": "#/$defs/SearchTargetInput"
+  },
+  "title": "Targets",
+  "type": "array"
+}

changedInput schema / required

Previous value: -[
-  "accounts"
-]New value: +[
+  "targets"
+]

First observedv0.1.4Aug 11, 2026

TDQS

C2.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, covering the safety profile. The description adds a result-size range (1-500), stable ordering, and optional paging, which are useful behavioral details beyond annotations, though 'stable mailbox order' is ambiguous.

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?

A single, front-loaded sentence with no wasted words. Efficient, though the phrasing 'metadata rows in stable mailbox order' is slightly jargon-heavy and could be clearer.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 13 parameters, zero schema descriptions, and an output schema that covers returns, the description is far too sparse. It omits all search criteria and filter semantics, leaving an agent unable to select or invoke the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not describe any of the 13 parameters. 'Optional paging' weakly hints at cursor/limit, but no meaning is added for filters like text, sender, subject, etc.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a verb ('Search') and resource ('metadata rows') but does not explicitly say 'emails' and lacks any differentiation from siblings like get_emails or list_emails. The purpose is implied by context but vague and not clearly distinguished.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus alternatives such as get_emails or list_mailboxes. No prerequisites, exclusions, or use-case scenarios are mentioned.

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

Deploy Server