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

Annotations already declare this is a non-destructive, idempotent write, and the description is consistent with that while adding the crucial behavioral gate (do not confirm until explicit approval). It still doesn't say what the sealed state means downstream (whether it can be reopened or amended), which limits it below a 5.

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 sentences, front-loaded with the action, followed by the precondition. The second sentence is a long enumeration but every item in it is meaningful approval criteria, so little is wasted.

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 two-parameter, approval-gated write with an output schema and full annotation coverage, the description supplies what the structured fields cannot: the state transition and the human-approval precondition. Only the post-seal lifecycle (irreversibility, next steps) is unaddressed.

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 coverage is 0%, so the description must carry the parameter burden. It explains the semantics of confirmed well (a deliberate approval gate), but invoiceId is left entirely to the schema and the const:true constraint on confirmed is never mentioned in prose.

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 precise verb and state transition ('Mark the current draft as the approved invoice'), which is clearly distinct from sibling lifecycle tools like begin_invoice, read_invoice, and accept_invoice_change. It does not explicitly name a sibling or contrast its behavior, so it falls just short of the top band.

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 an explicit precondition: pass confirmed=true only after the freelancer has approved the lines, quantities, rates, due date, late terms, and discount. This tells the agent both when to call it and when not to, which is exactly the guidance an approval-gated mutation needs.

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