generar_documento

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

Annotations only declare it is a non-read-only, closed-world, non-destructive write. The description adds real behavioral context beyond that: multi-format delivery, automatic retrieval of doctrine/jurisprudence from the local corpus when not supplied, full-text transcription of each cited norm, and the product rule «no se cita sin texto». It stops short of stating whether existing files are overwritten or where output lands.

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?

A single dense paragraph, front-loaded with what it produces and in which formats before moving to the «informe» special case and the citation rule. Every sentence carries information, though the run-on «informe» clause is heavy.

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 generator with no output schema, the description covers the output formats and the informe pipeline well, but leaves the civil/laboral/protección/PPA modes' expected inputs and the handling of optional fields unaddressed. Adequate for the flagship mode, incomplete for the rest.

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% across 18 parameters. The description meaningfully explains the informe-mode inputs (hechos, análisis, normas, doctrina, jurisprudencia auto-search), which compensates for several undocumented fields, but many parameters (rut, tribunal, demandante, demandado, peticiones, comparecencia, otrosies) and the non-informe modes get no semantic help 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 (generar) and resource (documento de trabajo) and enumerates the five concrete document types plus the output formats (Word .docx, HTML/MD/TXT/JSON). It also carves out the «informe» mode's distinct behavior, so an agent can tell it apart from the sibling recurso_proteccion_generar and export_brief_ojv.

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 type enum and the special «informe» branch imply when each mode applies, but there is no explicit when-to-use/when-not guidance and no mention of the overlapping siblings (recurso_proteccion_generar, compile_legal_dossier, export_brief_ojv). Usage must be inferred from the type list.

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