purchase_order_deleteRemove one purchase order with nothing received and never rendered, freeing that month's slot. One with a receipt is refused, naming it. The PO number is never reissued. purchase_order_receive logs arrivals.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Purchase order id such as PO-2026-0001, or an exact supplier name |
Changes observed during successful MCP inspections.
Input schema / additionalPropertiesRemoved value: -falseDoes the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds real value beyond them: the refusal condition, the fact that the error names the offending receipt, the quota effect ('freeing that month's slot'), and that the PO number is never reissued. No auth or confirmation requirements are mentioned, keeping it just short of 5.
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?
Four short sentences, front-loaded with the action and its preconditions, with no filler. The phrase 'never rendered' is compressed to the point of obscurity and costs a little clarity.
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 destructive single-parameter tool with no output schema, the description covers preconditions, failure behavior, and irreversibility of the PO number. It does not say what a success response looks like or whether confirmation is required, a minor remaining gap.
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?
With 100% schema coverage on a single parameter, the schema already documents 'id'. The description adds no clarification of the surprising schema detail that an exact supplier name is also accepted, which is the one place extra meaning would have helped.
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 plus the eligibility conditions ('nothing received and never rendered'), which distinguishes it from purchase_order_receive and the other PO siblings. The term 'rendered' is domain jargon left unexplained, slightly blurring the exact scope of what qualifies for deletion.
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?
Gives a clear eligibility rule (no receipt, never rendered) and states the refusal case, which effectively tells the agent when the call will fail. It points at purchase_order_receive for arrivals, but that is not a true alternative for this operation and no explicit 'use this instead of X when...' guidance is offered.
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.