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

The description adds real behavior beyond the safety annotations: which INPC months are used at each endpoint, the fallback to the last published INPC, truncation to four decimals, and the floor of 1. With readOnly/idempotent/destructive already covered by annotations, these domain rules are the added value, though the response shape and edge-case behavior (e.g. inverted period) remain unstated.

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?

A single dense sentence, front-loaded with the action and legal reference, with the exclusion clause last. Every clause carries information, though the mid-sentence enumeration of rules is packed and would read better as short ordered statements.

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 read-only pure-calculation tool with three documented parameters, all the computational rules an agent needs are present, and the description even hints at the return value when importe is supplied. Missing only the concrete output shape and behavior for invalid or inverted periods, which matters little given there is no output schema.

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, but the description adds meaning the schema does not: it explains that the two month parameters correspond to the INPC of the month preceding each endpoint, and that supplying importe triggers an additional updated-amount result. That mapping is not derivable from the schema alone.

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 ("Calcula el factor de actualización") plus the exact legal basis (Art. 17-A CFF) and the three objects it applies to (contribución, devolución, saldo pagado fuera de plazo). It also carves out what it is not ("No calcula recargos"), which is enough to separate it from the raw INPC siblings.

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 makes clear the situation that selects this tool (late payment, refund, or outstanding balance) and explicitly excludes recargos calculation. It does not name calcular_variacion_inpc or consultar_inpc as the alternatives for raw index data, so routing is implied rather than stated.

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