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

Annotations only cover readOnly/destructive/openWorld; the description adds substantive behavior beyond them: return fields, that the invoice is not emailed until send_invoice, the per-call confirmation default and its toggle, that the action 'reaches other people' requiring user confirmation, and the Cotlet API key requirement with app scoping.

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 purpose and scope, then capabilities, then safety/auth notes. Dense but each sentence carries actionable information; the auth sentence and the confirmation sentences are both justified given the openWorldHint and write nature.

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?

Despite having no output schema, the description enumerates what the call returns (number, tax, total, balance due), states side effects and delivery status, and covers auth requirements. An agent has everything needed to invoke it correctly and safely.

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 adds meaning beyond the schema: it explains layout semantics (service = free-text lines, item = item codes from the Items List, professional = records work dates) and that due_date overrides customer payment terms only when passed.

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 sales invoice for a customer with one or more lines') and names the scope (open invoice, returns number/tax/total/balance due). It also distinguishes itself from the sibling send_invoice, so an agent can tell it apart from myob_send_invoice, myob_get_invoice and myob_list_invoices without opening a schema.

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 signals context: the invoice is created open and 'is not emailed until you call send_invoice', which routes the agent to the sibling for delivery. It also flags that confirmation is on by default and can be disabled per tool. No explicit when-not-to-use case, but the creation-vs-delivery boundary is well drawn.

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