Buscando jurisprudencia

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

With no annotations this description carries the full burden, and it delivers: it discloses that the SPIJ index ignores 'tomo' (verified), that 'organismo' filters locally by scanning up to 5 pages, that internal page scanning happens per returned page, and the fallback fields ('sugerencias', 'organismos_disponibles'). That is unusually rich behavioral disclosure about partial results and limitations.

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-loads the purpose then organizes the rest into clear Args/Devuelve blocks, and nearly every line conveys actionable information (param syntax, verified limitation, return fields). It is long, but the length is justified by 11 undocumented parameters, keeping it dense rather than padded.

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?

With no output schema, the Devuelve block explains the return shape (ok, total, organismo, escaneadas, filtrados, siguiente_start, and conditional sugerencias/organismos_disponibles) and points to detalle_norma/texto_completo for full text. Combined with per-parameter guidance, an agent has everything needed to invoke and interpret this tool.

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 0% across 11 parameters, so the description must compensate – and it near-fully does. Every parameter is documented: consulta query syntax (implicit AND, no OR/quotes, '*' wildcard, start with 1-2 words), tomo, materia, organismo matching behavior, numero format, date range format, orden codes, start/paginas, and sumilla_chars limit semantics.

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 ('Busca jurisprudencia en el SPIJ') and the parenthetical '(TC, cortes, precedentes, sentencias)' scopes exactly what kinds of documents are returned. This cleanly separates it from the norms-oriented siblings such as buscar_normas and buscar_en_norma.

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?

Gives strong operational guidance: warns that 'tomo' is sent but NOT applied at index level, and explicitly calls 'organismo' 'la via correcta' for filtering, plus routes to listar_filtros for materias values. It lacks an explicit statement of when to prefer this tool over buscar_normas/buscar_en_norma, so it is clear context rather than full when/when-not framing.

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