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

Annotations already declare the safety profile (mutation, non-idempotent, non-destructive, closed-world). The description adds two useful behavioral facts: line items are keyed on quantity and unit_price, and restock defaults to false, which tells the agent whether inventory is affected. It does not disclose validation rules or response behavior, so it earns a solid but not rich 3.

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 with the core action front-loaded and no filler. It is efficiently sized, though the terseness contributes to the gaps elsewhere rather than compensating for them.

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 7-parameter mutation tool with 0% schema coverage and no output schema, the description leaves most parameters undocumented and omits any return/response behavior or validation expectations. It is not complete enough to call the tool confidently without inspecting the schema.

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 0% and there are 7 params. The description only illuminates the required 'lines' array (quantity + unit_price), which is genuinely valuable given the array items are an untyped object. However memo, reason, customer_id, customer_name, sales_order_id, and sheet_number get no explanation, and 'restock' is referenced even though it is absent from the schema (additionalProperties=false), which may confuse. Coverage is too thin.

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 first sentence 'Create a return' is a specific verb+resource but essentially restates the title 'Create return' with no differentiation from siblings like receive_return, cancel_return, or get_return. The remaining sentences describe parameters, not purpose. An agent knows roughly what it does, but the definition adds little purposeful framing beyond the name.

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?

There is no guidance on when to create a return versus when to receive one, cancel one, or list them, despite several closely related siblings. No prerequisites or context for invocation are stated. The agent must infer usage entirely.

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