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

Adds substantial context beyond the annotations: on-order quantities including existing drafts count against the target, items with no supplier are listed rather than silently dropped, dry_run creates nothing, and pricing is disclosed ($0.01 per draft order, nothing if none found). Mutating, non-idempotent, non-destructive annotations are consistent with the description for drafting orders that must be sent separately.

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-loaded with the central rule, which is good, but the cost sentence is duplicated verbatim in substance ('$0.01 per draft order' appears twice, the second time with 'nothing if none are found'). The first sentence is a long run-on that bundles quantity logic, pack rounding, and counts-of-existing-orders into one breath.

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 no output schema, the description carries return-value burden and does reasonably: it tells the agent drafts are created, unsupplied items are listed, and dry_run yields only a plan. It stops short of describing the shape of the result (draft order ids, per-supplier grouping) that an agent would need to then call purchasing_send_order.

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 coverage is 50%; dry_run is given real meaning in the description ('only shows the plan') beyond a bare boolean default, and skus is framed as a restriction to specific items. The skus behavior when items lack suppliers is described at the outcome level, though the description never states limits or how skus interacts with the reorder-point screen.

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 with full scope: draft one purchase order per supplier for every inventory item at or below its reorder point. The replenishment rule (preferred supplier's fixed quantity, or enough to reach twice the reorder point, raised to minimum order and rounded to whole packs) makes it unmistakable versus purchasing_create_order and purchasing_send_order.

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 positions the tool in a workflow: drafts are produced here, then 'You check and send them (purchasing_send_order)' — naming the follow-up sibling. The dry_run: true alternative is given for preview-only. It does not say when to use purchasing_create_order manually instead, so no full exclusion set.

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