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

Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=true, so the lower bar applies. The description still adds real behavior: 'WRITE:' labeling, the existing-record constraint (it will not create a vendor or item on the fly), auto-numbering unless a number is supplied, and the underlying POST endpoint.

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?

Four short clauses, front-loaded with the operation type and resource, then the scope constraint, then the confirmation rule. No redundancy and nothing buried.

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?

For a non-idempotent write with nested line items and no output schema, the description never says what comes back (PO id/number) for chaining into sosinventory_get_purchase_order, nor what happens when the vendor/item does not exist or the number collides. Annotations and a fully documented schema cover much of the rest, leaving a moderate 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 description coverage is 100% and nested objects are fully annotated, so the schema already carries parameter meaning. The description's only extra detail is auto-numbering, which the schema's `number` field already states ('leave out for automatic numbering'); nothing is added about unit_price-as-cost or date defaults beyond the schema.

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 ('creates a new purchase order') plus hard scope constraints: the vendor and items must already exist with line items. That scope plus the purchase-vs-sales distinction makes it separable from sosinventory_create_sales_order without opening a schema.

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 an explicit pre-call workflow rule ('Confirm the vendor, items, quantities and costs with the user before calling') and implies prerequisites through 'EXISTING vendor' / 'existing items'. It stops short of naming alternatives or stating when not to use it (e.g. drafts vs confirmed POs).

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