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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true; the description adds real behavioral context on top by disclosing the hidden side effect that supplying a quantity causes SOS to create an inventory adjustment at the location. It omits permission/auth requirements and the non-idempotent consequence of retrying (duplicate items), which the annotation only flags without explaining.

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 so the agent knows the mutation class immediately, then effect, then precondition. Nothing is padded and the endpoint is a useful trailing detail rather than a lead-in.

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 15-parameter creation tool with no output schema, the description covers the flow and the notable side effect well. What it never addresses is what comes back — whether the new item's id is returned so the agent can chain into sosinventory_get_item or a stock operation — which is the one real 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 67% and the description adds only one genuinely new fact — the category-scoped uniqueness constraint on name — plus a soft restatement of the initial_quantity/initial_location dependency already documented in the schema. The remaining 15 parameters, including nested vendor/category objects and the enum-typed 'type', are left to 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?

Opens with a specific verb+resource pair ("WRITE: creates a new inventory item") and immediately names the secondary effect (an inventory adjustment for opening stock). This clearly separates it from the create_* siblings (customer, vendor, purchase order, sales order) and from sosinventory_get_item.

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 a concrete precondition with a named alternative tool: check sosinventory_list_items first because names must be unique per category. It also frames the initial-stock path as optional. It stops short of any when-not-to-use guidance (e.g. don't use for services or for updating existing items — use an update tool instead).

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