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

With zero annotations the description carries the full burden, and it delivers meaningful non-obvious context: exactly which calendar is applied (BR national + banking holidays), the DU day-count convention, and a cost model ($0.005 USDC per call via x402, first call per tool per day free). What it omits is the payment/auth mechanics — what an agent must be prepared to do to satisfy x402, and what happens if payment fails.

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-loaded with the core purpose and operations, then calendar scope, then pricing, then an example. Each sentence earns its place; the inline JSON example is compact and illustrative. Slightly dense but no filler.

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?

No output schema exists, and the embedded example response compensates well by showing the exact return shape (mode, from, to, business_days, calendar). The one real gap is mode coverage: the `date` parameter's schema description references a 'check mode' that the description never explains or enumerates, leaving a documented mode undefined.

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 100%, so the schema already documents all four parameters including their mode assignment (from/to for count, date/add for add). The description adds only the DU convention and interval semantics on top of that, which is marginal beyond what the schema states. Baseline 3 is appropriate.

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+resource pair: 'Brazilian business-day calculator' with the two concrete operations (count between two dates, add N days to a date) spelled out. An agent can tell what it does at a glance, but nothing distinguishes it from the sibling 'holidays' tool, which plausibly covers overlapping calendar territory.

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 splits behavior by mode ('count business days between two dates … or add N business days to a date') and pins down the DU convention and half-open (from, to] interval, which is useful mode-selection guidance. It never says when to prefer this tool over 'holidays' or any other sibling, and offers no exclusions, so usage is implied rather than directed.

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