request_undoAsk the merchant to undo a publish (put back what it replaced, or remove an item it created). This does not undo by itself: the merchant clicks Undo on the card or on the link this returns.
| Name | Required | Description | Default |
|---|---|---|---|
| store | No | Which connected store (its myshopify address, e.g. other-store.myshopify.com). Leave it out for the default store; list_stores shows them. | |
| draft_id | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and idempotentHint=true, so the low-risk profile is covered. The description earns credit for the behavior annotations cannot express: the undo only happens after a human clicks on the returned card or link. It stops short of saying what happens if the merchant declines or how long the request stays valid.
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 tight sentences with zero filler; the meaning of undo is front-loaded and the critical caveat follows. Every clause carries information an agent needs.
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?
A simple two-parameter, non-destructive tool with no output schema, and the description covers the essential gap by noting that a card or link is returned. Minor omissions (the undocumented draft_id, what a declining merchant means for the caller) keep it below a 5.
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 50%: 'store' is documented in the schema but 'draft_id' — the only required parameter — has no description anywhere. The tool description does not compensate, never mentioning either parameter or explaining that draft_id identifies the published draft to be reverted.
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?
States a specific verb and resource ('ask the merchant to undo a publish') and immediately disambiguates what 'undo' means ('put back what it replaced, or remove an item it created'). An agent can tell this apart from request_publish or discard_draft without opening any 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?
Implies the usage context (reversing a prior publish) and gives one hard constraint — that it does not undo by itself. However, it never names alternatives such as discard_draft or edit_draft for reversing changes, and gives no explicit when-not-to-use guidance.
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.