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

Annotations already declare this is a non-readonly, non-destructive, non-idempotent, closed-world write. The description adds real value beyond that: a never-reused invoice number is returned, rounding happens per line before summing, mixed currencies are refused, and there is a free-tier limit of 3 per month. It still does not say whether the invoice is issued/finalized on creation or what a failed call leaves behind, which matters for a non-idempotent write.

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, front-loaded sentences that each carry a distinct fact: return value, units/rounding, currency constraint, quota. The telegraphic style is efficient, though fragments like 'Free: 3 a month' would read better as an explicit quota statement.

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 7-parameter create tool with no output schema, the description covers the return shape (record plus number), monetary units and rounding, currency agreement, and a rate limit. It is close to complete; the main omission is the lifecycle state of the created invoice and any consequences of auto-adding unknown clients.

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 100%, so the schema already documents every parameter, including unit_price in major units and the currency-agreement rule. The description reinforces the major-units convention and the round-then-sum ordering, which is a useful correctness cue, but adds little syntax or meaning the schema does not already carry.

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?

'Create an invoice from line items' states a specific verb and resource, and the 'from line items' framing implicitly separates it from invoice_from_hours. It never names a sibling outright, so the differentiation is inferable rather than explicit.

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?

There is no explicit when-to-use or when-not-to-use statement; the agent must infer that hour-based billing belongs to invoice_from_hours and that retrieval belongs to invoice_get. The 'one currency per invoice' rule gives some prep guidance, but nothing routes the caller between siblings.

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