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

Annotations already declare readOnlyHint=false/destructiveHint=false, so the write profile is partly covered. The description adds real context: it is saved unsent, reaches no one, needs no confirmation, and requires an API key with app access. These behavioral facts go beyond the annotations, though return/id behavior is not addressed.

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?

The opening sentences restate the same idea twice ('Invoice from a completed job or an approved estimate...' then 'Creates an invoice from a completed job, from an approved estimate...'), which is wasteful. Content is front-loaded and usable, but redundancy costs it 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?

For a create tool with no output schema, the description covers state (unsent), the follow-up tool (send_invoice), and auth requirements, which is nearly everything needed. It omits what the call returns (e.g., the new invoice ID), a minor gap.

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 100%, so the schema already documents every parameter. The description adds the notion that job/estimate/line-item inputs are alternative sources, but no syntax, format, or constraint detail beyond the schema.

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?

Names a specific verb (creates) and resource (invoice) and enumerates the three source modes: a completed job, an approved estimate, or custom line items. It clearly reads as distinct from siblings like yardbook_send_invoice and yardbook_get_invoice.

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?

Explicitly routes the agent: 'It is saved unsent; send_invoice emails it,' naming the alternative tool and the condition that selects it. No explicit when-not-to-use beyond that, but the source-mode framing (job vs estimate vs line items) further guides selection.

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