generate_draft_pos

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

Since no annotations are provided, the description carries the behavioral disclosure burden. It usefully reveals that execution is a create-on operation, offers a dryRun escape hatch to avoid creating documents, and exposes the edge case that items without a preferred vendor are skipped and reported in skippedNoVendor. It does not state whether the resulting POs are draft/posted or what happens on partial failure, but the description is substantially transparent for a create-style tool.

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?

Three sentences with no filler: purpose, dryRun behavior, and skip edge case are all front-loaded and necessary. Every sentence earns its place, and the structure makes the tool's core behavior easy to absorb.

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?

The central workflow, dryRun option, and one important edge case are covered. However, there is no output schema and the description only hints at return values via skippedNoVendor; an agent does not know what a successful run returns (e.g., PO identifiers or statuses). For a tool that creates multiple documents, missing return and failure semantics are a clear 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 coverage is about 75% (items, dryRun, and docDueDate are described), so the baseline is already fairly high. The description adds real meaning by explaining that items are grouped by DefaultVendor and that dryRun previews grouping without document creation. It does not add detail for comments or warehouseCode, but those are straightforward and not a major gap.

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 names a specific action and result: group items-with-antities by preferred vendor and create one Purchase Order per vendor. It also states the grouping key (DefaultVendor on the item master), which clearly differentiates it from siblings like create_purchase_order and create_po_from_quotation. This is a concrete, non-tautological definition.

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?

It clearly defines the intended scenario: a list of items to procure that should be grouped by vendor, and it explicitly suggests dryRun:true for a non-destructive preview. It does not name create_purchase_order as an alternative or state when not to use the tool, so there are no explicit exclusions. Overall, the context is clear though routing guidance is implicit.

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