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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world computation, so safety is fully covered. The description adds 'Returns tax due and effective rate', but that is largely redundant given an output schema exists, and it omits any caveats about regional rate assumptions.

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 short sentences, purpose front-loaded, no filler. It earns most of its space except for the redundant return-value statement and the inaccurate input list.

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 needn't be explained, and annotations cover safety. The material gap is the phantom 'region' input that the schema does not support, leaving an agent unsure whether regionality is chosen or implicit.

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% and defines amount and relationship, so the baseline would be 3. But the description asserts 'Inputs: region, amount, recipient relation' – 'region' is not a parameter at all, which is misleading, and 'recipient relation' loosely renames the relationship enum without adding meaning.

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 names a specific verb and resource (compute Belgian donation tax) and scopes it to three regions, which separates it from the many other Belgian tax siblings like calculate_belgian_income_tax. However, it claims a 'region' input that the tool cannot actually take, slightly muddying 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?

'Use for estate planning in Belgium' gives a clear use context, and it points to list_bundles for related calculators. But there are no when-not conditions and no direct naming of an alternative sibling tool, leaving the routing guidance implicit.

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