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

Annotations already declare readOnly, non-destructive, closed-world behavior, and the description adds genuinely new context: no personal data is required or returned, the escrito carries bracketed placeholders instead, and modules only activate when the corresponding facts are supplied. It does not describe the shape of the delivered document (plain text, sections, numbering), which is the main remaining behavioral 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 purpose and legal basis, then module logic, then the privacy constraint. The personal-data point is stated twice ("No pide ni devuelve datos personales…" and "No le pidas esos datos y no los escribas en la llamada"), which is emphatic but mildly redundant.

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 20-parameter drafting tool with no output schema, the description supplies the legal purpose, the conditional module behavior, and the privacy contract, which is substantial. The one unaddressed element is what the returned escritos look like structurally, which an agent would otherwise infer only from the bracket-placeholder remark.

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% and each of the 20 parameters (including the five enums) is already documented in the schema. The description adds the cross-parameter logic (base reguladora module needs baseAplicada/baseCorrecta or baseMalCalculada; omission of the EVI propuesta triggers a subsidiary retroacción request), but does not go field by field, so baseline 3 is appropriate.

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?

"Compone la reclamación previa ante la entidad gestora (INSS, ISM, mutua…) que deniega una prestación" gives a specific verb, the exact instrument produced, and the addressee. It is also distinguishable from the sibling demanda_juzgado_social because it states that this is the prior step required before suing.

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 clearly states when this tool applies (a benefit-denial resolution from the managing entity, as the prerequisite for later litigation) and gives an inclusion rule for each module ("Cada módulo entra solo si el caso lo afirma"). It does not explicitly name the sibling to use when the deadline has passed or when the claim is already filed, so usage is clear but not fully routed.

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