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

Annotations already carry destructiveHint=true and idempotentHint=false, so the description's added value is the seal-state rule and the hand-off to accept_invoice_change for changing a sealed discount. That is real behavioral context beyond the structured fields, though it never says whether a new discount replaces an existing one.

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?

Four short sentences, each load-bearing: the action, the kind/value mapping, the sealed-invoice rule, and the anti-fabrication constraint. Nothing is padded and the core action is front-loaded.

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?

An output schema exists, so return values need no explanation, and the parameter and lifecycle rules are covered well enough to call it correctly. Only the unexplained 'note' parameter and the unspecified replace-vs-add behavior on unsealed invoices keep it short of 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?

With 0% schema description coverage the description must carry the load, and it does for the hardest part: it ties each 'kind' enum to the meaning of 'value' (none uses 0, percent is a whole number 1-100, fixed is whole minor units). The required 'note' and 'invoiceId' parameters receive no explanation, leaving a small gap.

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 description states a specific verb and resource ('Record a discount the freelancer is putting on the invoice') and scopes it to the invoice workflow shared with siblings like seal_invoice and accept_invoice_change. An agent can distinguish this from place_line or quote_line_rate without opening a schema.

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?

It gives clear operating context: the discount is the freelancer's, and after sealing a different discount is refused until accept_invoice_change applies an apply_discount suggestion, which tells the agent when this call will and won't succeed. There is no explicit when-to-use versus a sibling alternative, but the workflow condition is spelled out.

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