cancel_scheduled_emailCancel a pending scheduled email by scheduleId before it sends; the draft remains in Drafts, so message content is not lost.
Cancel a pending scheduled send by scheduleId (from send_email with sendAt, or list_scheduled_emails). The draft stays in the Drafts folder, so the content is not lost.
| Name | Required | Description | Default |
|---|---|---|---|
| scheduleId | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes |
Changes observed during successful MCP inspections.
v0.19.0Input schema / properties / scheduleId / maxLengthAdded value: +512v0.11.1Output schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"v0.11.0Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "data": {
+ "additionalProperties": false,
+ "properties": {
+ "draftId": {
+ "type": "string"
+ },
+ "draftKept": {
+ "const": true,
+ "type": "boolean"
+ },
+ "scheduleId": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "scheduleId",
+ "draftId",
+ "draftKept"
+ ],
+ "type": "object"
+ }
+ },
+ "required": [
+ "data"
+ ],
+ "type": "object"
+}v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly=false, idempotent=true, destructive=false; the description adds the meaningful consequence that the draft survives in the Drafts folder, so content is not lost. That confirms and explains the non-destructive annotation rather than repeating it. It doesn't cover edge behavior such as cancelling an already-sent schedule, but with annotations carrying the safety profile this is solid.
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?
Two sentences, front-loaded with the action and identifier, followed by the one behavioral fact that matters. No filler.
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?
Output schema exists, so return values need not be described, and the non-loss guarantee is covered. The remaining gap is failure/edge semantics (invalid scheduleId, schedule that has already fired), which would help for an idempotent mutation but is a minor omission for a one-param tool.
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 coverage is 0% and the single parameter is undocumented in the schema, so the description must compensate — and it does by identifying the provenance of scheduleId (generated by send_email with sendAt, or retrievable via list_scheduled_emails). It doesn't state format/constraint details, but the provenance is the semantically important part.
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?
Specific verb+resource ('Cancel a pending scheduled send') plus the keying parameter (scheduleId), which separates it cleanly from siblings like list_scheduled_emails and send_email. An agent can identify the operation 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It tells the agent exactly where the scheduleId comes from ('from send_email with sendAt, or list_scheduled_emails'), which implies the workflow context for use. It stops short of naming when NOT to use it — e.g. delete_draft as the alternative when the user wants the content gone entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.