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

Annotations only declare write/openWorld/non-destructive, but the description adds real behavioral context: the invoice is drafted not sent, Dubsado auto-numbers it, the issue date is the invoice date, due_date spawns a one-payment plan, and a >$0 invoice appears in the client portal before emailing. This is well beyond the annotation payload and consistent with it.

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?

Front-loaded with the core action and the 'Not emailed yet' constraint, and each sentence carries information. There is mild redundancy between 'Draft an invoice in a project from your packages or line items' and 'Creates an invoice in a project from saved packages, line items, or both'.

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 4-param write tool with no output schema, it covers creation, sourcing, numbering, date semantics, portal visibility, confirmation behavior, and the follow-up tool. Nothing an agent needs to call it correctly is 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 coverage is 100%, so the baseline is 3, but the description clarifies semantics the schema only hints at: due_date creates a payment plan (not just a date field) and the invoice date equals the issue date. It adds genuine meaning over the structured fields.

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 and resource ('Draft an invoice in a project') plus the source of line content ('from your packages or line items'). It explicitly separates itself from the send_invoice sibling, so an agent can route without inspecting schemas.

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?

Names the alternative ('Email it with send_invoice') and the condition that selects it ('Not emailed yet'). It also states the confirmation policy ('you confirm each call; you can switch that off') and the user-confirmation requirement for a tool that reaches other people.

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