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

No annotations exist, so the description carries the full burden; it discloses the non-obvious credit cost, which is useful. It implies a read-only lookup but says nothing about behavior on weekends/holidays, how far back dates are supported, or what happens with future dates — meaningful gaps for a date-parameterized API call.

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?

One front-loaded sentence that moves from what is returned, to the entity, to the allowed kinds, to the cost. No filler, no redundancy.

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 simple 2-parameter, no-output-schema tool, the core is covered — 'compra/venta' signals the return shape. But with no annotations and the description doing all behavioral work, the lack of any statement about date bounds, holidays, or error cases leaves an agent without guidance in edge cases.

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 compensates: it enumerates the casa values and glosses 'bolsa' as MEP, domain knowledge not derivable from the raw enum, and constrains fecha to a past date (the schema only supplies the YYYY-MM-DD format). It does not state whether casa is case-sensitive or what a valid date range is.

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?

Names a specific verb+resource: buy/sell dollar exchange rate for Argentina on a past date, and enumerates the quote types (oficial, blue, bolsa/MEP, contadoconliqui, mayorista, cripto, tarjeta). An agent immediately knows what is retrieved and for which dimension of the currency market; no sibling does spot/historical FX so no conflict exists, though no sibling differentiation is offered.

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?

'en una fecha pasada' implies the tool is for historical lookups rather than current quotes, which is real usage guidance, and the 1-credit cost warns of a metered call. However, no alternatives are named and nothing states what to do for other scenarios (e.g. current rate, non-business days), so usage is implied rather than spelled out.

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