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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world, so the safety profile is covered by structured data. The description adds genuinely new behavioral context: the object stays an unapproved draft until seal_invoice, and the currency/amount representation contract for downstream calls. It does not address what happens on duplicate invocation, but that is largely covered by idempotentHint=false.

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?

Three short sentences, front-loaded with the core action, then constraints, then unit conventions. Dense and largely waste-free, though the final sentence about amounts is slightly tangential since no amount parameter exists here.

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 not be described, which relieves some burden. Still, for a 4-required-parameter creation tool with 0% schema coverage, three parameters (title, number, clientName) remain completely undefined for the agent.

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% across 4 required parameters, so the description must compensate. It clarifies that currency is a three-letter code and that amounts are minor units of that currency (relevant to later tool calls), but title, number, and clientName are left entirely unexplained in both schema and description.

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?

"Start a draft invoice" is a specific verb+resource, and the description explicitly contrasts the draft stage with seal_invoice, so the agent can place it in the invoice lifecycle. It does not, however, distinguish it from the other draft-mutating siblings (place_line, set_invoice_due, offer_discount) that presumably operate on an invoice created here.

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 sentence about seal_invoice implies this is the entry point of the workflow before any commitment is approved, which is useful implied guidance. There is no explicit when-to-use/when-not statement (e.g., whether it must precede place_line, or what happens if an invoice already exists).

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