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

Annotations already establish readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description still adds real context beyond them: 'Nothing is stored or sent' confirms a stateless, side-effect-free call, and it explains the post-call flow (PDF download in the builder, optional Stripe pay link with partial payments), which is behavior the agent cannot get from annotations.

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 tightly written sentences: purpose and output first, downstream flow second, the no-storage guarantee last. No filler and nothing buried at the end that belongs at the front.

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?

With 15 parameters, nested objects, and no output schema, the description usefully compensates by naming the primary return value (builderUrl) and the human follow-up path. It omits mention of the only required parameter (items) and currency default, but those are adequately covered by the schema, leaving the definition complete enough to call correctly.

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 73%, so the schema largely documents itself, including taxRate ('applied after discount, not to shipping'), discount, and shipping in minor units. The description's parenthetical '(subtotal, tax after discount, shipping, total)' restates that ordering rather than adding new meaning, so the baseline 3 is appropriate.

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?

The description gives a specific verb and resource ('Price an invoice') and names the concrete return artifact ('builderUrl that opens the ... builder prefilled'), which is more than a restatement of the name. It implies a distinction from render_invoice_pdf by pushing PDF download into the builder UI, but it never names that sibling, so the differentiation is inferential rather than explicit.

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?

Usage is implied: use this to price/draft an invoice and hand the human a builder link, with PDF export and Stripe pay links happening downstream. There is no explicit when-to-use guidance or when to prefer render_invoice_pdf or prepare_invoice_template instead, so the agent must infer the boundary.

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