create_ruleCreate an automation rule for one inbox account.
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"rule": "<rule>"
},
"name": "create_rule"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| rule | Yes | ||
| emailAddress | No | ||
| emailAccountId | No |
Changes observed during successful MCP inspections.
Input schema / properties / emailAddress / patternPrevious value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"Input schema / properties / rule / properties / actions / items / properties / fields / anyOfPrevious value: -[
- {
- "properties": {
- "bcc": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "cc": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "content": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "folderName": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "label": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "subject": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "to": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "webhookUrl": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- }
- },
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "properties": {
+ "bcc": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "cc": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "content": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "folderName": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "label": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "subject": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "to": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "webhookUrl": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / rule / properties / actions / items / properties / messagingChannelId / anyOfPrevious value: -[
- {
- "format": "cuid",
- "pattern": "^[cC][^\\s-]{8,}$",
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "format": "cuid",
+ "pattern": "^[cC][0-9a-z]{6,}$",
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / rule / properties / condition / properties / aiInstructions / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]Input schema / properties / rule / properties / condition / properties / aiInstructions / typeAdded value: +[
+ "string",
+ "null"
+]Input schema / properties / rule / properties / condition / properties / static / anyOfPrevious value: -[
- {
- "properties": {
- "from": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "subject": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "to": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- }
- },
- "type": "object"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "properties": {
+ "from": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "subject": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "to": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": "object"
+ },
+ {
+ "type": "null"
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the write/risk profile is covered. The description adds only the single-account scoping hint; it says nothing about irreversible side effects of rule actions (DELETE, SEND_EMAIL, CALL_WEBHOOK all appear in the schema), whether rules run retroactively on existing mail, or execution limits, which is significant for a tool with destructiveHint=true.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no wasted words. It is efficient, though that efficiency is partly achieved by omitting content the tool's complexity calls for.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a create tool whose schema contains nested conditions and a large action enum with destructive effects, and with no output schema and no parameter descriptions, the description is far too thin. An agent knows what it is for but not how to assemble a valid rule payload or what will happen when it runs.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so all three parameters — including a deeply nested rule object with 16 action types, conditions, and delay/channel fields — are undocumented in structured data. The description must compensate but only implies that the rule belongs to one inbox account, leaving emailAddress vs emailAccountId and the rule payload structure unexplained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description has a specific verb and resource ('Create an automation rule') and adds scope ('for one inbox account'), so an agent can distinguish it from get_rule, list_rules, update_rule and delete_rule by name and text. It stops short of explicitly naming those siblings or the conceptual relationship between them, so it is clear but not maximally differentiated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to create a rule versus updating an existing one, nor any mention of prerequisites such as needing a valid inbox account. The phrase 'for one inbox account' hints at scoping but does not tell the agent which input field carries that account or that it is required.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.