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

Annotations already declare this is a non-read-only, destructive, non-idempotent mutation, so the safety profile is covered. The description adds genuine state-machine context beyond the annotations — the invoice-seal precondition and the fact that re-rating is refused post-seal — which is exactly the kind of behavioral trait annotations cannot express.

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?

Two tight sentences with the core operation front-loaded and the seal constraint second. 'The rate already chosen' is slightly indirect phrasing, but there is no padding or redundancy.

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 three-parameter mutation with an output schema, the description covers the essential constraint an agent needs (sealed invoices reject new rates) and points to the change-request path. Missing auth/permission requirements and the meaning of 'already chosen' keep it just short of fully complete.

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. It meaningfully clarifies rateMinor as a whole number of minor units in the invoice currency, which the bare integer schema (1..100000000) does not convey, but invoiceId and lineId remain completely unspecified.

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 ('Set the rate ... for one line') and specifies the unit as minor units of the invoice currency, which pins down the operation precisely. It does not explicitly contrast itself with siblings like set_line_quantity or offer_discount, but the resource-level specificity is enough to identify the call.

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 real usage condition: after the invoice is sealed, a different rate is refused, and the named alternative is accept_invoice_change applying a change_rate suggestion. This routes the agent away from this tool in the sealed case, though it says nothing about authorization or the pre-seal workflow.

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