Invoice PDF

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

Goes well past the annotations by disclosing the rounding contract (half-up to the currency's minor unit, with named 3-decimal and 0-decimal currencies), formatting style, multi-page continuation for long item lists, Latin-only limitation, and the return payload (PDF path plus computed totals). It also implicitly discloses a filesystem write via the output parameter, which sits in mild tension with readOnlyHint but is conventional for a document generator that only creates a new artifact.

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 the purpose and the artifact, then the high-value details (math, pagination, Latin-only, return value). The long parenthetical field inventory is largely redundant with a fully-described schema and is the one clause that does not fully earn its space, but the rest is dense and useful.

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 14-parameter, nested-object tool with no output schema, the description covers what the agent must know before calling: what gets rendered, how money is computed and formatted, that long lists paginate, the Latin-only restriction, and what comes back (path + totals). No output schema is needed given that return description.

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 already 100%, so the baseline is 3; the description earns an extra point by explaining computation semantics the schema does not — discount applied before tax, per-line rounding to the currency minor unit, en-US formatting with examples (JOD 10.124). It does not clarify logo path-vs-base64 handling or the 300-item ceiling, which remain schema-only.

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 artifact ("Make a clean A4 invoice PDF") and then enumerates exactly what the document contains — issuer block, client, invoice number/dates, line items, totals, notes, terms, PAID stamp. That level of specificity makes it unmistakable against siblings like doc_receipt or ai_markdown_to_pdf without opening any 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?

Usage is only implied: the field list and the closing "Latin text only for now" and web-version link hint at scope, but there is no explicit when-to-use/when-not-to-use statement and no named alternative (e.g. doc_receipt for receipts, ai_markdown_to_pdf for arbitrary PDFs). The web link is a reference, not routing guidance.

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