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

The description clearly discloses the preview mode behavior ('Returns a preview unless confirm=true is set'), which is a critical safety trait. It also notes optional recording of paid amount and payment date. However, it does not mention permissions or idempotency behavior, though the latter is documented in the schema.

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?

The description is two concise sentences that efficiently communicate the tool's purpose, key behavior (preview/confirm), and optional features. No filler 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 write operation with no output schema, the description does not explain the return value beyond preview, nor does it describe the effect on the invoice (e.g., changes to status or payments). While sibling context may suffice, the description itself lacks full completeness.

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?

The description mentions 'Optionally record the paid amount', but the input schema has no 'paid_amount' parameter. This is misleading and adds confusion. All four schema parameters are documented in the schema itself (100% coverage), so the description adds negative value here.

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 clearly states the verb 'Mark' and the resource 'invoice as Paid', and specifies the required state 'issued or sent'. This distinguishes it from sibling tools like issue_invoice, reissue_invoice, void_invoice, etc., which handle other states.

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?

The description implies usage after invoice is issued/sent, but does not explicitly state when not to use it or provide alternatives. No guidance on prerequisites or edge cases.

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