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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered; the description adds real behavioral context by disclosing the catalog size, the three-level structure and the exact fields returned. It does not mention response ordering or whether the price/level summaries inflate the payload, which keeps it below 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?

Three sentences, no filler: content of the listing first, selection criteria second, follow-up routing last. Every clause carries information an agent needs to choose or chain the call.

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 a single optional parameter, no output schema and read-only annotations, the description supplies everything needed to call and chain correctly, including the returned fields in lieu of an output schema. The only gap is the inconsistent lesson count (32 vs. 26 in the schema), which leaves the agent unsure of the unfiltered result size.

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 enum for 'nivel' is already documented in the schema, so the description only needs to complement it, and it does mention the three levels by name. However, it never explains the 'nivel' filter and its stated total of 32 lessons conflicts with the schema's 'Sin él, devuelve las 26 lecciones', which could mislead an agent reasoning about unfiltered results.

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 names a specific verb and resource (listing the course lessons) and enumerates exactly what each entry contains: slug, title, description, level, access method, plus price and per-level summary. It explicitly separates itself from the siblings that operate on a single lesson (ver_leccion, leer_leccion) and from topic search (buscar).

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?

It states two concrete use cases (show the full syllabus, obtain a lesson slug) and an explicit exclusion with an alternative: 'para un tema concreto es mejor buscar'. It then routes the returned slug to ver_leccion for the public sheet or leer_leccion for the full text, so the agent knows the follow-up call as well.

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