generar_documento

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: the concrete output artifacts and their format (editable .docx, A4, justified, plus HTML/MD/TXT/JSON), the auto-retrieval of doctrine/jurisprudence from local material, the integral transcription of cited norms, and the governing rule "no se cita sin texto". Gaps remain around permissions, latency, and failure behavior, but this is well above the annotation-free baseline.

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 core action and outputs before the type list and the 'informe' elaboration. It is dense and runs long with stacked parentheticals, but nearly every clause carries information and the closing product rule "no se cita sin texto" is a clean, memorable anchor.

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 an 18-parameter tool with no annotations, no output schema, and only 50% schema description coverage, the description covers outputs, types, and informe behavior but never maps which parameters are required for which 'tipo' (e.g. whether a demanda civil needs demandante/tribunal) nor how output-format selection works. Adequate but with clear gaps for this complexity.

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 50% on 18 parameters, so the description must compensate. It adds real meaning for the 'informe' workflow (normas transcribed in full with citation and link, doctrine/jurisprudence auto-searched when omitted, dictamen behavior) but leaves roughly half the parameters, including type-specific ones like demandante/demandado/tribunal/peticiones, with no cross-parameter context in the description.

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+resource ("Genera un documento de trabajo completo") with concrete output formats (Word .docx editable, A4, justified text, plus HTML/MD/TXT/JSON) and enumerates the document types matching the 'tipo' enum. It is highly specific, but it never addresses its overlap with the sibling recurso_proteccion_generar, which appears to cover the 'proteccion' type.

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?

Implicitly tells the agent which document types are supported and that doctrine/jurisprudence are fetched automatically "cuando no se las entregan", which is useful routing info. However, there is no explicit when-to-use-this-vs-X guidance for closely related siblings such as recurso_proteccion_generar or compile_legal_dossier.

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