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

Annotations only provide readOnlyHint=true, which already signals a safe read. The description adds valuable behavioral boundaries: it does not compute the family business reduction and instructs the agent to avoid presenting the result as an estimate when a business is involved. This goes beyond the annotations without contradicting them, though it could specify output format or assumptions about preexisting wealth more explicitly.

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?

The description is moderately long but every sentence carries critical information: purpose, exclusions, and a routing instruction. It is front-loaded with the primary function, and the 'IMPORTANTE' warning is clearly demarcated. It could be slightly tighter, but there is no filler or 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?

Given the tool has no output schema, the description does well to mention that it produces a 'cuota' (tax amount) and to warn against presenting it when the business exclusion applies. It covers scope, exclusions, and alternative tooling. It is less explicit about the exact output structure or assumptions about the 'coeficientes por patrimonio' parameter, but overall it is sufficiently complete for an agent to select and invoke the tool correctly.

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?

The input schema has 100% description coverage for all five parameters, so the baseline is 3. The description adds some context (e.g., 'coeficientes por patrimonio' and 'bonificaciones autonómicas') that helps interpret the calculation, and it clarifies the scope of group_parentesco to 'donaciones en vida entre familiares'. However, it does not add detailed parameter-specific semantics beyond what the schema already provides.

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 opens with a specific verb and resource: 'Calcula el Impuesto de Donaciones (ISD) en España', and further scopes it to 'donaciones en vida entre familiares'. It also names a sibling alternative ('comparar_donacion_vs_herencia') and explicitly lists an exclusion (empresa familiar), so the agent can distinguish this tool from nearby calculators 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?

The description gives explicit when-to-use and when-not-to-use guidance: it is for lifetime donations between family members, it must not be used when family business reductions are involved, and if the user is comparing donation vs inheritance, the agent is told to use 'comparar_donacion_vs_herencia' instead. This is direct, actionable routing to the correct alternative.

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