generate_free_invoice

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

With no annotations, the description usefully discloses that the tool is stateless and does not persist to a tenant account, which is genuine behavioral context. It leaves out auth requirements, whether the returned preview URL expires, and whether generation has side effects or limits.

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?

A single dense sentence with the key constraint ('stateless', not saved) front-loaded. Efficient, though the parenthetical could be integrated more smoothly and no structural breaks aid scanning.

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?

No output schema, no annotations, and 0% schema coverage on a nested 5-parameter input means the description carries the full burden, and it under-delivers. It never describes the shape of the returned calculation or preview URL, nor the item/issuer/client fields an agent must supply.

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 0% and there are 5 parameters including nested objects and arrays, yet the description explains none of them. It mentions VAT breakdown, hinting at vat_percent per item, but issuer/client structure, currency default, and optional invoice_number are wholly undocumented.

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 ('generates structured invoice calculation') plus output artifacts (VAT breakdown, A4 printable preview URL). The 'stateless public tool' framing and 'does not save to a tenant account' clearly separate it from sibling tools like verify_invoice_qr, though no sibling is named explicitly.

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?

The stateless/public framing implies this is a one-off calculation-and-preview tool rather than an account operation, and the 'does not save' clause implies when-not. However, no explicit when-to-use guidance or named alternative is given for scenarios like verifying or persisting an existing invoice.

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