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

With no annotations, the description carries the burden itself and does add two real facts: a hard precondition (no receipts) and an authorization scope ('Owner or office'). It does not say whether cancellation is reversible, whether the PO is voided vs deleted, or what happens to any recorded bills or linked invoices.

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?

Twelve words, front-loaded with the action, then the precondition, then the permission scope. No sentence is wasted and nothing important trails at the end.

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 explained, and the guard plus auth note are the essentials. Still, for a mutation with zero annotation coverage, the omission of reversibility and downstream effects (bills, receipts partially posted) leaves a meaningful 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?

Schema description coverage is 0% and the description never mentions po_id or where to obtain a valid UUID. The single parameter is self-naming enough that an agent will infer it, but no value is added beyond the schema.

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 plus resource ('Cancel a purchase order') qualified by a guard ('that has nothing received'), which also separates it from po_receive and po_undoReceipt. An agent can tell this is the terminal void-style action on a PO without opening a 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?

Explicitly gives the condition for use ('nothing received') and the required precursor ('undo receipts first'), which maps to the po_undoReceipt sibling. It stops short of naming that sibling or stating what to do instead if the PO has already been billed.

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