Explain what happened to an email
explain_emailDiagnose a single email's outcome after a bounce, complaint, or failure by returning the verdict, supporting evidence, retry feasibility, and callable remediation steps.
Instructions
Purpose: understand one message's outcome and act on it. Use it after a bounce, a complaint or a failure instead of guessing. NOT for: the raw timeline (get_email), or the state of the whole key (why_was_this_not_sent). Returns: the verdict, the evidence behind it (diagnostic code, feedback type, transport reason), whether retrying the identical send can work, and remediation as callable steps — each carrying the method, path and body. A step with no call is one only a person can do.
Tool call template
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": {
"email_id": "<email_id>"
},
"name": "explain_email"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| email_id | Yes | The message id returned by send_email. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Identifier. | |
| error | No | Present instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds. | |
| status | No | ||
| actions | No | ||
| verdict | No | ||
| evidence | No | ||
| retryable | No | ||
| what_happened | No |