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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description adds real behavioral context on top: this is a draft-to-approved state transition gated on explicit human sign-off. It does not spell out irreversibility or what happens to the draft record, which keeps it from 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, no filler: the action is stated first, then the gating condition. Every clause earns its place and the sequence matches how an agent should reason about calling it.

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 annotations cover the safety/idempotency profile. What remains — the required human-approval gate and the draft-to-approved transition — is fully covered, leaving nothing an agent needs missing.

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 parameter meaning, and it does for the non-obvious one: confirmed true is permitted only after explicit approval of specific invoice elements, which is exactly the semantics an agent needs. invoiceId is left implicit as 'the current draft', which is mildly ambiguous given the schema only says uuid.

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 ('mark') and resource ('the current draft') and names the resulting state ('the approved invoice'), which is easily separable from siblings like begin_invoice or read_invoice. It stops short of explicitly contrasting itself with adjacent tools such as accept_invoice_change, so it lands at a clear-but-undifferentiated 4.

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 for invocation: pass confirmed true only after the freelancer approves the lines, quantities, rates, due date, late terms and discount. That is unusually concrete usage guidance. It does not name an alternative tool or a when-not case, so it is not a full 5.

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