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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial domain behavior beyond them: the 15%–22.5% banded rates, the 25% low-tax-jurisdiction rate, buyer withholding, resident exemption testing, and the FR1/FR2 reduction factors. The pre-1996 exclusion is a concrete boundary the structured fields do not express.

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?

Front-loads jurisdiction and purpose, then compresses the resident/non-resident branches into a single dense sentence with no filler. It is slightly over-packed: unexplained tokens like 'FR1/FR2' and 'upper limit' cost the reader without adding selection value.

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?

For a 6-parameter calculator with no output schema, the description covers the key domain mechanics (rates, withholding, exemptions, cutoff year) so an agent can judge applicability. Gaps remain around the default when the optional seller is omitted and around what the calculation returns, but the core is sufficient.

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 50%, and the description partially compensates by explaining the seller enum branches and the resident exemption/lower-bound mechanics that underlie reinvested and only_property. However, it never maps meaning onto the bare required fields (sale_price, purchase_cost, purchase_year) and the FR1/FR2 reference is unexplained jargon, so half the parameters remain under-specified.

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 (income tax on the gain from selling a home) and immediately scopes it by jurisdiction (BRAZIL) and seller class (resident vs non-resident). An agent can distinguish it from siblings like purchase_costs_br or transfer_tax_us 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?

Gives clear conditions for each branch: non-residents are 'computed in full' with buyer withholding, residents get 'exemptions tested' with the FR1/FR2 reduction factors, and purchases before 1996 are explicitly out of scope. It never names a sibling alternative to use instead, so it stops short of full when/when-not routing.

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