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

With readOnlyHint already present, the description still adds substantial behavioral detail: fixed amount per child, current amount and maximum children sourced from data/fiscal, payment in 14 pagas, and the legal change removing extra requirements for men. This goes well beyond the structured annotations and prevents misinterpretation of the sexo parameter.

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 dense but well ordered: purpose, calculation mechanics, key legal update, and eligibility requirements. Every sentence earns its place, and the STJUE/STS note is essential because it materially changes who qualifies.

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 complex legal calculation with seven parameters and no output schema, the description covers purpose, legal context, eligibility, and calculation data sources. It could explicitly describe the exact return value, but the fixed per-child amount and schema descriptions make the output largely inferable.

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. The description adds meaning by explaining that the complement is a fixed amount per child, that the current amount and child cap come from data/fiscal, and that it is paid in 14 installments. The remaining parameter-level details are already handled well by the input schema.

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 states a specific action ('Calcula el complemento de pensión...'), identifies the legal basis (art. 60 LGSS), and scopes it to contributory retirement, permanent disability, and widowhood pensions. This clearly distinguishes it from related sibling tools that calculate pensions or retirement gaps.

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?

It provides explicit eligibility requirements: contributory pension, fact causante from 4 February 2021, at least one child, and the other parent not receiving the complement. It also clarifies the post-2025 equality rule so men are known to be eligible. It stops short of naming sibling alternatives or giving explicit 'use X instead' routing.

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