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

readOnlyHint=true already tells the agent this is a safe read, so the bar is lower; the description still adds real behavioral content by disclosing the exact cost model behind each route, the exemption that applies, and what the response contains (cheapest option plus caveats like pactos sucesorios and plusvalía municipal). It does not cover edge-case failure modes or input validation limits, which is the only remaining gap.

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 scenario label and the trigger questions, followed by the computation model and the prioritization rule. Dense but every sentence carries selection value; the emphatic casing and 'PRIORIZA' framing are slightly promotional but functional.

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 16-parameter read-only calculator with no output schema, the description adequately previews the return (cheapest route plus qualifications) and frames the domain. Given how many optional inputs exist, a sentence on which are truly needed for a first-pass comparison would have closed the gap.

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 baseline is 3; the description earns an extra point by explaining the causal chain the key parameters feed into — donor age plus habitual residence driving the IRPF exemption, and plusvalía municipal requiring the catastral values — which contextualizes why inputs like the acquisition year and value matter. It stops short of mapping individual optional parameters.

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 scope: computes and COMPARES the total fiscal cost of transferring a property now by both routes, spelling out what each route includes (donation = gift tax + donor IRPF; inheritance = inheritance tax, donor IRPF exempt). It also names the sibling tools it supersedes (calcular_donaciones, calcular_sucesiones), so an agent can distinguish it without opening a 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 literal user phrasings that should trigger the tool ("¿es mejor donar un piso a mi hijo en vida o esperar a la herencia?") and an explicit rule to prefer it over the single-scenario siblings, including those on other servers. This is both when-to-use and when-to-use-something-else.

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