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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), so the description's main added value is the auto-numbering behavior and the confirmation requirement, both genuinely useful. However, it says nothing about side effects beyond creation (inventory allocation/reservation, price-floor enforcement is only in the schema), and the non-idempotent, open-world nature is left entirely to the annotations.

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 tight sentences, front-loaded with the 'WRITE:' marker and the core action, followed by the constraint and the pre-call confirmation rule. The trailing POST endpoint adds integration context without padding; nothing is redundant.

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 an 8-parameter nested mutation with no output schema, the description covers preconditions and the confirmation workflow well. The one real gap is the return value: the agent isn't told whether the created order (its id or assigned number) comes back, which matters since a follow-up get_sales_order call would need that identifier.

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%, so the baseline is 3; the description still adds a bit by explaining that the order number is auto-assigned unless one is passed, which frames the optional 'number' field as a fallback rather than a requirement. The remaining parameters (date, comment, customer_po, location, line-level pricing) are left to the already-verbose 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 sales order') and immediately scopes it to an existing customer with existing line items. The parenthetical exclusion ('a customer or item cannot be created inside an order: use the create tools first') cleanly separates it from the sibling create_customer/create_item tools.

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 prerequisite (customer and items must already exist, create them first) plus a workflow rule ('Confirm the customer, items, quantities and prices with the user before calling'). The schema further routes to sosinventory_list_customers and sosinventory_list_items for lookup, so alternatives are named rather than implied.

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