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

Annotations say only readOnlyHint=false and destructiveHint=false; the description adds substantial behavioral context beyond that - the invoice is always a draft, never issued/emailed/charged, cannot trigger AutoPay, and requires at least one line item. It also discloses the underlying API call (POST /invoices with draft=true).

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 tight sentences, front-loaded with the write/draft nature, then the finalization condition, then the minimum requirement and API mapping. No filler.

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 an 11-parameter write tool with no output schema, the description covers the essential behavior and constraints. Return-value details are absent, and the description doesn't map to the injected customer_id reference, but the core call semantics are complete.

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 82%, so the schema already documents most parameters. The description still adds value by stating the 'at least one line item' constraint that justifies the required items array, going beyond per-parameter descriptions.

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 ('create a DRAFT invoice for a customer') and emphasizes the draft state that distinguishes it from any future issue/finalize tool. An agent can identify this immediately as the invoice-creation tool among read-oriented siblings like invoiced_get_invoice and invoiced_list_invoices.

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?

Clearly frames this as creating a draft that must be finalized by a person in Invoiced before any issue/email/charge/AutoPay occurs, which implicitly scopes it. It does not name an alternative finalize/send tool or state explicit when-not conditions, so a 4 rather than a 5.

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