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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the description only needs to add context — and it does: the catalog is a filtered subset of all votes, results come back most-recent-first with 'texto' acting as a relevance signal, and every response carries 'url' and 'atribucion' with a CC BY 4.0 citation obligation. Rate limits and error/empty-result behavior are not covered, keeping it short of a 5.

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?

Four sentences, front-loaded with purpose, then scope and ordering, then the catalog restriction, then the attribution obligation. Dense but each sentence carries distinct information; the licensing sentence is the longest and could be tightened, but nothing is padding.

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?

No output schema exists, yet the description explains the return set (ordering, 'texto' ranking, 'url'/'atribucion' fields) and warns about the limited catalog plus where the rest lives. For an 8-parameter, all-optional read tool that is close to sufficient; only pagination/limit behavior and empty-result handling are left implicit.

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?

With only 50% schema description coverage, the description carries real weight: it enumerates the searchable axes (palabras, tema, legislatura, resultado, fechas), mapping to texto, tema, legislatura, resultado, desde and hasta, and adds semantics the schema lacks by noting that 'texto' also drives relevance ranking ('las más ajustadas a la búsqueda'). 'limite' and 'pagina' are left unexplained, which is a modest gap.

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 and resource ('Busca votaciones del Pleno del Congreso de los Diputados') plus the scope (legislaturas XIV y XV, desde febrero de 2020) and the searchable dimensions (palabras, tema, legislatura, resultado, fechas). It does not explicitly contrast itself with the sibling 'ver_votacion' (list vs. detail), so an agent must infer the split between the two 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?

Explicitly delimits when the tool applies ('Solo las votaciones con ficha en la web: votaciones finales de leyes, convalidaciones de reales decretos-leyes y las que tienen resumen') and routes everything else (enmiendas, mociones…) to a named alternative, the portada search engine with its URL. That is genuine when/when-not guidance with an alternative, not just implied context.

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