zenfulfillment_cancel_ordersWRITE, cannot be undone: cancel orders by reference (up to 50). Only orders that can still be cancelled (before the warehouse has packed or shipped them) are cancelled; the others come back in errors. Confirm the references with the user first. POST /orders/cancel.
| Name | Required | Description | Default |
|---|---|---|---|
| references | Yes | Order references to cancel (as in the Reference column, e.g. the ZF reference or your own order number). |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds crucial context beyond them: the operation cannot be undone, partially-ineligible orders fail per-item and surface in `errors`, and user confirmation is required. This is exactly the behavioral detail an agent needs before invoking a destructive tool.
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?
Front-loads the critical 'WRITE, cannot be undone' warning, then the action, the eligibility caveat, the confirmation instruction, and the endpoint. Every clause carries information; nothing is wasted.
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 single-parameter destructive tool with no output schema, the description covers safety, eligibility, partial-failure return behavior (`errors`), and the endpoint. Nothing essential for correct invocation is missing.
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 100% and the `references` parameter is well documented in the schema itself. The description restates the 50-item cap (already in maxItems) and the reference format, adding little beyond what the schema provides, so the baseline 3 applies.
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 ('cancel orders by reference') with a scope limit (up to 50) and a clear warning that this is a write operation. An agent can distinguish this from sibling read tools like list_orders or get_order without consulting 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?
Clearly sets the precondition for use ('only orders that can still be cancelled, before the warehouse has packed or shipped them') and instructs the agent to confirm references with the user first. It does not name a sibling alternative for inspection, but the usage context is explicit.
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.