invoice_extract

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

With no annotations, the description carries the full burden and does so well: it discloses the two processing paths (deterministic XML parsing vs. Claude Haiku for PDFs/photos), the validation performed (totals, EU VIES VAT ID, IBAN/BIC), the EN 16931 authenticity check, the 15 MB size limit, the $0.02 USDC per-call cost, and p99 latency of 8000ms. This is unusually rich behavioral context.

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?

Purpose and supported formats are front-loaded, followed by method, validation, limits, and cost — a logical order. It is dense and slightly run-on with em-dash chains, but nearly every clause (output fields, processing method, cost, latency) earns its place.

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 exists, so the description must describe returns — and it does, enumerating number, dates, seller/buyer with VAT ID, line items, tax per rate, totals, IBAN, and payment terms. Combined with size, cost, latency, and validation disclosures, an agent has everything needed to call it correctly.

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 100%, so every parameter is already documented in the schema, establishing the baseline of 3. The description corroborates the input formats and the validate behavior but adds no syntax, precedence, or mutual-exclusion detail beyond what the schema provides.

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 — 'Invoice data extraction' — plus the exact input formats (PDF, photo, XRechnung/ZUGFeRD/Factur-X XML) and the JSON fields returned. It is clearly distinguishable from generic siblings like pdf_extract, ocr, and doc_parse because it is scoped to structured invoice data with accounting-specific output.

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?

Gives clear context for when it applies: EU e-invoices, PDFs, and photos are all supported, and it explains that e-invoices are parsed deterministically while plain PDFs/photos go through a model. However, it never names an alternative sibling (e.g. ocr or pdf_extract) or states when NOT to use it, so routing is left partly to inference.

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