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

Annotations only declare readOnlyHint/openWorldHint, so the description carries real weight here and delivers: per-call price, x402 on Base or Solana, the failure mode (PaymentRequirements returned instead of a result), and the exact remediation (_meta "x402/payment" then retry). That is genuinely actionable behavior an agent cannot get from annotations. It stops short of rate limits, failure modes beyond payment, or what a successful response looks like.

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?

The price is stated twice in near-identical wording ("Costs $0.03 USDC (x402)" then "Paid: $0.03 USDC per call via x402"), and the bracketed block mixes docs attribution ("falcon.sol docs.") with operational detail. The useful scoping sentence is front-loaded, but the body 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?

Payment and auth behavior are well covered, which is the hardest part. But with no output schema and no required parameters, the description should explain what a successful extraction returns and how url vs file_base64 are resolved — neither is addressed, leaving real gaps for a paid call.

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 67% — url and file_base64 are documented in the schema, but the type enum (auto, invoice, receipt, purchase_order, w9, bank_statement, generic) has no description anywhere, and the description adds nothing about how type changes extraction or what "auto" triggers. Baseline 3 is appropriate since the schema does most of the work.

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?

"Full extraction of all pages" gives a verb (extract) and a scope (all pages), but never says what is extracted — text, structured fields, or typed financial data — nor which document format. It also never names the obvious sibling preview_document, so the agent must infer the full-vs-preview distinction from the scope word alone.

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 description gives no when-to-use guidance relative to preview_document or the other finance siblings; the only procedural text is about the payment retry loop. It also does not state that one of url/file_base64 must be supplied despite required parameters being empty.

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