cancel_purchase_order

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description adds genuinely non-derivable context: the cancel is a soft state change, the record is retained, and nothing is deleted. It does not state whether cancellation is reversible, whether approvals are required, or what happens if the confirmation code is stale, and 'nothing is deleted' mildly softens the destructiveHint framing without contradicting it.

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?

The irreversible-effect caveat is front-loaded in the first two sentences, then a compact Args block covers each of the three parameters in one line each. No restatement of the tool name, 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?

An output schema exists, so return values need not be described. Parameters, the soft-cancel semantics, and the preview prerequisite are all covered for a 3-param mutation. What remains unaddressed is failure behavior — missing, expired, or mismatched confirmation codes — which an agent calling a destructive operation would benefit from knowing.

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 0%, so the description carries the full burden, and it does: po is identified as the purchase order ID, reason as the rationale, and confirmation_code is given provenance (obtained from preview with the identical argument set). That provenance detail is the single most important thing an agent needs and is absent from the schema entirely.

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 a purchase order') with an added effect clause ('stays on record as cancelled; nothing is deleted'). An agent can distinguish it from siblings like amend_purchase_order or reject_purchase_order by verb alone, but the description never explicitly contrasts those adjacent operations in the same approval workflow.

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?

The confirmation_code documentation encodes a clear workflow: call preview("cancel_purchase_order", <these same args>) first, then call this tool with the returned code. That is concrete, actionable guidance tied to a named sibling. It stops short of saying when cancel is the correct choice versus amend or reject.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.