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

The description asserts 'Calling this changes nothing', i.e. a read-only, side-effect-free call, while the annotations declare readOnlyHint=false and idempotentHint=false, which assert that the call is not guaranteed read-only. An agent reading both gets contradictory signals about whether invoking this tool mutates state, which is precisely the side-effect question it needs answered.

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?

Purpose is front-loaded and the preview/confirmation sentences earn their place, but the 'Money is integer minor units (cents)' sentence is irrelevant to a schema with no monetary field, and the annotation-conflicting 'changes nothing' claim occupies prime real estate.

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 explains what a call returns (a preview of changes plus a confirmation link) and who can complete the action. But it omits any parameter guidance for a 5-parameter tool and leaves the side-effect question inconsistent with the annotations, so it is not complete enough to be trusted alone.

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 80%, so the schema already explains orderNumber, items, carrier and carrierName; only trackingNumber is undocumented. The description contributes no parameter meaning at all, and its one data-format remark ('Money is integer minor units (cents)') refers to no parameter in this schema, so it is at best neutral and at worst noise.

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 opening sentence gives a concrete verb+resource ('Mark an order as sent'), and the rest immediately qualifies it by saying the call only previews. However it never distinguishes itself from close siblings such as orders_mark_delivered, orders_update_shipment or orders_mark_paid, so an agent must still infer its niche from the name alone.

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?

Usage is only implied: by stating that nothing changes and that 'only the merchant, on that page, can make it happen', it communicates that this is the first/preview step of a two-party flow. It names no alternative tool and gives no explicit when-to-use/when-not conditions relative to the shipment-related siblings.

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