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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description nonetheless adds real behavioral context: full-text vs title matching, the es_texto_normativo flag marking normative text, aviso_versiones warning that editions are not marked as current, and the articulos_de_revista sub-results. What it does not do is describe ranking, pagination limits, or the timeout ceiling — the latter is instead carried by the rows parameter description in the schema.

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 matching semantics in the first sentence, then layered warnings, so the most important information survives skimming. It is long and the emoji-laden warnings add visual noise, but nearly every sentence carries distinct operational content rather than filler.

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?

There is no output schema, and the description compensates fully by enumerating the returned fields (título, autores, editorial, páginas, isbn13) plus the conditional ones (es_texto_normativo, aviso_versiones, articulos_de_revista con autor y temas). For a three-parameter read tool it leaves nothing an agent needs to call it correctly or to interpret the response.

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 100% and the schema itself is unusually rich, including the ~30 s gateway timeout guidance for rows. The description adds meaning not in the schema by tying result fields to the sibling tool's parameters (isbn13, articulo, clave), but it says nothing about how terminos is interpreted (multiple terms, AND/OR, stemming), which is the one parameter an agent most needs to understand.

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 (búsqueda de libros y publicaciones jurídicas dominicanas) and, crucially, the matching semantics: the hit is in the full text of the work, not the title, with concrete examples («anatocismo» devuelve el Diccionario Jurídico Dominicano). It also separates itself from leer_doctrina (which serves the text) and from buscar_legislacion (which does not hold codes), so an agent can pick it out among 25 siblings.

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?

Explicit when-to-use ("Úsala para saber A QUÉ DOCTRINA acudir"), explicit hand-off (pass the isbn13 to leer_doctrina, the clave for Revista Saber y Justicia articles), and an explicit exclusion/correction: codes and reglamentos are in this library but NOT in buscar_legislacion, so search them by title here. It even states the read-before-attributing rule.

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