Buscar normativa de un regulador sectorial

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

No annotations are provided, so the description carries the full burden. It discloses that most results are PDFs without extractable text, that vigencia is often not published, and where it appears it's only the portal's own claim. It details divergent filter behaviors across entities (Invima requires text/year, Superfinanciera/Supertransporte stay in current year, ANM ignores year for circulares) and advises specifying a year explicitly. This is exceptional transparency.

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 long but well-structured with clear sections: scope definition, explicit 'CUÁNDO NO USARLA', then a paragraph on PDF/vigencia caveats, then a dedicated section on filter divergence. It is front-loaded with purpose and exclusions. Every sentence earns its place given the tool's complexity; it is dense but not 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 tool with 7 parameters and many entity-specific behaviors, the description covers purpose, exclusions, filter caveats, vigencia limitations, and hints that responses include metadata about which behavior was applied ('Cada respuesta dice cuál de estas cosas hizo'). It doesn't detail the exact return format, but that's not required without an output schema. The only minor gap is pagination behavior across entities, but that's inferable from the parameters.

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 71% (limite and pagina lack descriptions), but those are self-explanatory pagination parameters. The description adds significant semantic value beyond the schema: it explains how the 'texto' and 'anio' filters behave differently per entity, and warns about the need to specify a year for certain entities. It also clarifies 'entidad' by saying each entity declares its sector and limits, and mentions 'solo_entidad' behavior indirectly. This goes well beyond the schema's basic descriptions.

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 verb (buscar) and resource (actos administrativos de reguladores y ministerios sectoriales) with a clear exclusion: 'que el Gestor Normativo NO cataloga.' It explicitly contrasts with siblings resolver_cita and buscar_por_tema, so an agent can immediately tell this tool apart from the national-law tools.

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?

A dedicated 'CUÁNDO NO USARLA' section explicitly says to use resolver_cita or buscar_por_tema for leyes and decretos nacionales, and warns that the Decreto Único Reglamentario of each sector is already in the Gestor. It also directs to resolver_cita for real vigencia. This is explicit when-not-to-use and alternatives.

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