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

Annotations already declare this is a non-idempotent, non-destructive write, so the safety profile is clear. The description adds that the result is a draft rather than a submitted order, which is real behavioral context, but it says nothing about required line fields, validation, or what happens on duplicate submission.

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?

Two short sentences with zero waste; the purpose is front-loaded and the only parameter hint follows. Nothing is padded or repeated.

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?

With 6 parameters, a nested lines array whose items expose no properties, and no output schema, the agent needs far more than two field names to construct a valid call. The relationship between supplier_id and supplier_name, currency defaults, and the remaining required line fields are all unaddressed.

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% across 6 parameters, so the description must carry the load. It names only two nested line fields (quantity_ordered, unit_cost) and says nothing about memo, currency, supplier_id, supplier_name, or sheet_number, nor what else a line object requires — a significant shortfall for a nested array of untyped objects.

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?

The description states a specific verb and resource ('Create a draft purchase order'), so the agent knows exactly what is produced. The word 'draft' usefully distinguishes the outcome from submit_purchase_order, but no sibling is named or contrasted, leaving full differentiation implicit.

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 only usage signal is the word 'draft', which implies this runs before submit_purchase_order, but nothing states when to use this versus import_order or how it relates to receive/cancel flows. No exclusions or prerequisites are given.

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