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

Annotations already mark this as read-only, idempotent, and non-destructive. The description adds substantial behavioral context: it does not call the Tax Authority, requires buyer-authorized TA access for official verification, labels buyer-attested results as not independently authenticated, fails safely when buyer context is missing, costs $0.25 USDC, and returns deterministic reason codes. No contradiction with annotations.

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?

Four compact sentences with high signal-to-noise. The core purpose is front-loaded, followed by return behavior, cost, important caveats about external verification, and the recommended preview step. No filler or redundant restatement of the tool name.

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?

Given the 21-parameter schema, nested object, paid nature, and no output schema, the description covers the most important operational context: cost, return decision values, failure mode, external dependency limitations, and buyer-attestation semantics. The main gap is that it could more explicitly describe the expected structure of the PAY/HOLD/BLOCK result for an agent parsing it downstream.

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 only 19%, so the description must compensate. It does group parameters into meaningful categories: VAT and total arithmetic, date/amount/VAT component, allocation-number conditions, supplier registry identity, and vendor-risk signals. However, it does not explain many optional fields or the nested official_verification object's role in enough detail, so parameter semantics remain only partially clarified.

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: a PRE-PAYMENT GATE for an Israeli tax invoice that returns PAY, HOLD, or BLOCK. It distinguishes itself from siblings by describing the invoice-payment decision scope and explicitly routing to preview_israeli_invoice_payment_gate_free for the free first pass.

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 clearly says 'Use preview_israeli_invoice_payment_gate_free first,' which conveys the expected paid-vs-free workflow. It does not explicitly list exclusions or when to choose assess_israeli_vendor_payment_risk_paid instead, but the gate purpose is specific enough that the main alternative is named.

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