s21_save_questions_to_bank

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose persistence to a local SQLite database and the type of content stored (distractors, academic justification), which adds value beyond the name and schema. However, it omits duplicate handling, idempotency, permissions, return values, and error behavior, leaving important behavioral aspects undisclosed.

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 main action is front-loaded and the first sentence gives the essential persistence and categorization details efficiently. The uppercase flow directive is slightly intrusive but is clearly separated and provides actionable context for the agent.

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 mutation tool with a rich nested schema and no annotations, the description adequately explains what is stored and includes an explicit follow-up action. It would be more complete with duplicate-save behavior or expected response details, but those are secondary for correct selection and invocation.

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?

The input schema already describes 100% of the top-level and nested parameters, so the baseline is 3. The description only reinforces the mapping between domain concepts like 'materia, módulo, lectura y tema' and schema fields without adding new parameter-level facts.

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 clearly states a specific action ('Guarda un lote de preguntas de examen') and a concrete resource ('base de datos SQLite local'), making the purpose unambiguous. It also distinguishes this tool from read-only siblings like s21_get_bank_questions and generative tools like s21_generate_practice_quiz. The categorization clause adds useful precision without obscuring the action.

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?

The 'DIRECTIVA DE FLUJO' explicitly instructs the agent to invoke s21_open_exam_simulator after saving or when the student expresses intent to practice, which is clear contextual guidance. However, it does not explicitly state when not to use this tool or compare it against alternatives, so it stops short of full exclusions.

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