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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new behavior: exact minor-unit arithmetic, versioned rates, and refusal of unsupported rates, plus a 'not tax advice' disclaimer. It stops short of describing rounding presentation or the returned shape.

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?

Three packed sentences with zero filler; the core operation is front-loaded and the arithmetic/refusal caveats and disclaimer follow in priority order. Nothing could be deleted without losing information.

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?

There is no output schema, so the description carries the burden of saying what comes back, and it never does — an agent cannot tell whether the VAT portion alone, the gross, or both are returned for each mode. Combined with the undocumented tax_year range, this leaves real gaps for a financial calculation tool.

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 only 33% (only 'amount' documented), so the description must compensate. It partially does: 'net or VAT-inclusive NIS amount' explains the semantics of amount_includes_vat, and 'supported tax years' gestures at tax_year. But it never states the 2024-2026 bound or the default of false, leaving half the parameters underspecified relative to the coverage gap.

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 ('Calculate') and resource ('standard-rate VAT') plus the input form (net or VAT-inclusive NIS), which cleanly separates it from siblings like income_tax_calculator_il. The year scoping and 'Not tax advice' boundary further pin down what the tool is.

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?

Usage is only implied: 'for supported tax years' and 'unsupported rates are refused' tell the agent there are limits, but the actual supported window (2024-2026) lives only in the schema. No explicit when-to-use-vs-alternative routing is given, though siblings are different enough that little is needed.

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