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

Annotations only give destructiveHint=true and readOnlyHint=false; the description goes well beyond by disclosing the dry-run/commit split ('that call does not write, delete, cancel, or send'), token expiry of 5 minutes, single-use semantics, and that a 'confirm' boolean is ignored. It is consistent with the destructive annotation while explaining exactly where the mutation occurs.

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?

Six short sentences, front-loaded with identity, then effect, then the calling protocol. Each sentence supplies a fact an agent would otherwise get wrong; nothing is repeated from the schema or annotations.

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?

With no output schema, the description usefully enumerates the first call's return payload (confirmation_required, summary, confirm_token). It does not say what the committing second call returns (e.g., the assigned order number), which is the one gap for a tool whose whole point is producing that number.

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 0%, so the description must carry the load, and it does: confirm_token is explained as a value returned by the first call, to be repeated with identical arguments on the second, expiring in 5 minutes and usable once. order_id is self-evident as the target draft, so nothing material is left undocumented.

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 ('Confirm a draft sales order') and immediately adds the observable effect: it assigns the sales order number used on shipping marks. That effect distinguishes it functionally from update_sales_order, ship_sales_order, and cancel_sales_order without needing either schema opened.

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?

Clear on the condition that selects this tool (the order is a draft) and exhaustive on the two-step calling protocol, including what the first call does and does not do. It does not name alternatives such as update_sales_order for editing a draft, so guidance is strong but not fully routed against siblings.

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