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

No annotations exist, so the description carries the burden. It discloses the payment flow, pricing (25 sats/page), dual-model pipeline, and robustness claims. The caveat about hallucinated JSON for non-receipts is present in the schema but not in the description, so the description alone understates that risk.

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?

Five sentences, each information-dense: purpose, method, output, robustness, and pricing/payment. No filler or redundant phrases; front-loaded with the core action.

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?

Covers purpose, return JSON fields, payment prerequisite, and edge-case handling. Since there is no output schema, listing the fields compensates. The hallucination warning is in the schema, so overall the description is complete for a paid extraction tool, though it could have briefly noted non-receipt handling.

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 100%, so baseline is 3. The description adds context for paymentId by referencing create_payment and hints at documentBase64 format via 'multi-page invoices' and 'crumpled receipts' — slightly beyond the schema's basic parameter description.

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 clearly states 'Extract structured data from receipts, invoices, and financial documents' — a specific verb plus resource scope. It distinguishes itself from sibling tools like extract_document by narrowing to financial paperwork, and adds detail about the dual-model pipeline and output fields.

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?

Provides clear usage context: requires create_payment, pay-per-request with Lightning, and no API key needed. It does not explicitly name a sibling alternative or state when not to use this tool, but the purpose and prerequisite are well explained.

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