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

With no annotations provided, the description carries the full burden, and it discloses the most decision-critical behavior: the $0.13 USDC payment and the fact that oversized documents are rejected before OCR (i.e., before incurring cost). This is exactly the high-value context an agent needs for a paid tool; what is missing is any note on side effects or failure modes beyond the size rejection.

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?

Two sentences, about 25 words, with the most critical facts front-loaded (cost first, then resource, format, page limit, and rejection behavior). Every clause earns its place and nothing is redundant.

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 paid tool with a nested schema and no annotations, the description adequately covers cost, format, and page scope. However, it leaves meaningful gaps: the semantics of the 'expected' field are unexplained, and the relative use of document_url versus document_base64 (neither required) is unaddressed, though the output schema partially offsets the need to document return values.

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%, so the description must compensate, but it only adds a marginal hint that 'PDF/image' maps to the mime_type enum. The 'expected' nested object — the apparent core of the preflight concept, containing tax, total, line_items, etc. — is completely unexplained, and there is no guidance on choosing between document_url and document_base64.

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 states a clear function — OCR on PDF/image invoices — plus a specific scope ('up to 10 pages'), which distinguishes it from the sibling invoice_preflight_50_pages by page limit and from invoice_preflight_quote by document type. The verb 'process' is somewhat generic, but the OCR framing and page constraint make the purpose unambiguous.

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 page ceiling ('up to 10 pages') plus 'Oversized PDFs are rejected before OCR' gives an explicit, actionable boundary for when this tool applies versus the 50-page sibling. It does not name alternatives explicitly, but the page-count criterion is the operative routing signal and it is stated clearly.

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