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

Annotations already indicate readOnlyHint=true, so no contradiction. The description adds important behavioral context: it clarifies that the deduction reduces taxable base (not tax directly) and that it estimates savings using the marginal rate. It also specifies legal articles and amounts. This goes beyond typical calculation descriptions, though it does not detail all edge cases or assumptions.

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 a single paragraph of about 4 sentences, efficiently conveying purpose, legal basis, amounts, and behavior. It front-loads the main action. It could be slightly more structured (e.g., bullet points for amounts) but is concise and clear without wasted words.

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 and 4 parameters, the description lacks explicit mention of return values or expected output format. It states it 'calculates' and 'estimates savings' but does not specify whether it returns a single number, a breakdown, or an object. For a complete understanding, an agent might need to infer the output from context. Additionally, it does not address potential errors or prerequisites (e.g., tax year).

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% with each parameter having a description. The tool description adds meaning by explaining the amounts associated with the 'grado' parameter (e.g., 3,000€ for 33%-64%) and the additional 3,000€ for assistance needs, which enriches understanding of 'necesita_asistencia'. However, it does not explicitly describe the 'titular' or 'tipo_marginal' parameters beyond the 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 clearly states the tool calculates the minimum for disability in IRPF, with specific legal references (Ley 35/2006, arts. 60-65) and amounts based on disability degree and assistance needs. It also explains it estimates tax savings using marginal tax rate and notes it reduces taxable base, not tax directly. This specificity distinguishes it from sibling tools like calcular_irpf or other deduction calculators.

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 implies use when calculating the disability deduction in Spanish IRPF, but it does not explicitly state when to use this tool versus alternatives (e.g., other deduction calculators or general IRPF estimator). No explicit 'when not to use' or comparison with siblings is provided, leaving some ambiguity for an AI agent.

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