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

With no annotations, the description carries the full burden. It does disclose two non-obvious traits: the tool only records the status change and does not itself dispatch anything ('the agent or a person sends it'), and a permission/actor scope ('Owner or office'). It says nothing about reversibility, what happens if the PO is not a draft, or side effects on downstream status.

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?

A single, front-loaded sentence with the action and target state first and the clarifying parenthetical second. No filler, though the trailing 'Owner or office' is terse enough to be ambiguous rather than informative.

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 state-transition semantics are covered. But for a mutation tool with zero annotations, the description omits error conditions (non-draft PO), undo path, and whether the supplier is actually notified — all material for safe invocation.

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?

There is one required parameter (po_id) with 0% schema description coverage, so the schema supplies only type and uuid format. The description's 'a draft purchase order' does tie po_id to a draft-state PO record, which adds mild meaning, but no lookup guidance or validation constraints are given.

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 (mark) plus resource (purchase order) plus target state (sent to supplier), and the 'draft' qualifier pins down the source state. It is clearly distinguishable from siblings like po_receive, po_cancel, and po_update without naming them, though no sibling is explicitly contrasted.

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 'draft' precondition implies when this tool is applicable, and the parenthetical clarifies that the tool records the act rather than performing the delivery. However, it names no alternatives (e.g., use po_receive when goods arrive, po_cancel to void) and gives no when-not guidance.

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