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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds real behavioral context beyond them: no browser/account/storage needed, unknown/unsupported text is rejected rather than silently replaced, and it does not send invoices or take payments.

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?

Four tight sentences, front-loaded with the capability and immediately followed by constraints. Minor redundancy where it re-lists required inputs already captured by the schema, but no padding.

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 13-parameter nested tool with no output schema, the description conveys the crucial edges: input text restrictions, explicit error behavior, and non-goals. The return (a downloadable PDF) is named. It could say more about the error payload or the checkout-preload behavior, but it is adequate.

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 69%, and the nested item fields (quantity, unitPrice, currency, taxRate, discount, shipping) are documented in the schema. The description only restates the required inputs at a high level ('sender/customer names, invoice number, dates and complete line items'), adding little syntax or unit 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?

States a specific verb+resource: 'Generate a downloadable PDF artifact', and adds useful scope boundaries ('without a browser, account or storage', 'Does not send invoices or process payments'). It does not, however, explicitly differentiate itself from the siblings draft_invoice or prepare_invoice_template, so the agent must infer the distinction.

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?

Gives an explicit alternative for the unsupported case ('unsupported characters or logos return an explicit error, use the web builder for those') and negative scope ('Does not send invoices or process payments'). It stops short of saying when to pick this over draft_invoice, but the conditional routing is clear.

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