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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real behavioral detail beyond that: it returns exact net, VAT and gross values rounded to cents, which tells the agent the precision contract and avoids floating-point surprises.

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?

Two sentences, zero filler, and the core capability is front-loaded before the return-value detail. Every clause 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?

Output schema exists, so return values need not be explained, and annotations cover the safety profile. The description covers purpose, mode semantics and rounding, leaving only minor edge cases (e.g. rate 0) unaddressed for a simple deterministic calculator.

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 the baseline is 3. The description still adds units context the schema does not state explicitly: the rate is a plain percent value ('e.g. 21 for Dutch BTW'), which anchors how the agent should pass rate. That is a modest but genuine improvement over the schema.

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 (calculate VAT) and covers both directions of the operation: adding VAT to a net amount and extracting it from a gross amount. An agent can distinguish this from every unrelated sibling (csv_to_json, validate_iban, etc.) without opening the schema.

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 frames the two usage contexts (net amount vs gross amount) that map onto the add/extract modes, so the agent knows which direction applies. It gives no explicit exclusions or alternatives, but no sibling tool overlaps with VAT arithmetic, so there is nothing to route away from.

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