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

Goes well beyond the annotations by disclosing side effects and constraints: SKU lines create Inventory at the ordered unit cost, receiving is all-or-nothing, over-receipt is refused, the order transitions to partial or received, and the call costs $0.01 (nothing on failure). The non-idempotent annotation is reinforced by the all-or-none semantics.

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 purpose and packs a lot of decision-relevant detail into four sentences with no filler. The telegraphic phrasing ('at the order's location (or location)', 'All lines or none') is efficient though slightly rough to parse.

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?

Complete enough to call correctly: input alternatives, currency rule, overflow handling, state outcome, and cost are all covered, and there is no output schema to explain. Return payload details (what the receipt record looks like, how partials are represented) are the only 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 80% schema coverage the baseline is 3, and the description adds real meaning: line numbers are as the order lists them, all: true means everything still to come, unit_cost is only needed when the order's currency differs from the item's, and location overrides the order's default. Only the date parameter is left to the schema alone.

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 (record what arrived) on a specific resource (a sent purchase order), with the exact input shape (lines [{line, quantity}] or all: true). It is clearly distinguishable from siblings such as purchasing_send_order, purchasing_close_order, and inventory_move.

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 clear context — the order must already be sent — and an explicit alternative for the over-delivery case (take the extra in with inventory_move). It also explains the all: true shortcut vs itemized lines. It stops short of an explicit 'do not use this to...' exclusion, but the routing guidance is solid.

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