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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds the useful financial context that this 'never sends money', but the phrase 'This records an observed settlement' is ambiguous for a read tool and could momentarily suggest a write, and it says nothing about what data or format is returned.

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 short sentences, front-loaded with the purpose and followed by the key safety caveat. No filler.

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 simple one-parameter read tool with no output schema, the definition is roughly adequate, but it never indicates what 'derived amounts' actually contains or how the saved rate relates to the invoice, leaving the agent guessing at return semantics.

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 would ideally explain the single 'input.invoice_id' parameter. It does not mention it at all, though the schema field name and uuid format make the intent largely self-evident for one required parameter.

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 ('Read') and specific resource ('saved billing/settlement exchange-rate information and derived amounts'), which clearly separates it from the mutation siblings like set_invoice_settlement and clear_invoice_settlement. It does not name those siblings explicitly, but the read-vs-write distinction is inferable.

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 the word 'saved' and the read framing; there is no explicit statement of when to call this instead of set_invoice_settlement, clear_invoice_settlement, or preview_clear_invoice_settlement. An agent can infer read-only retrieval, but nothing is spelled out.

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