get_my_grades

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds a non-obvious behavioral detail: the tool does not register a visit to the grade report. This is meaningful context beyond the structured annotations and helps the agent reason about side-effects. No contradiction exists.

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?

A single, front-loaded sentence conveys the core action, the scope, and a critical behavioral note. There is zero redundancy; every word earns its place. The structure is ideal for quick parsing by an 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 simple read-only tool with one optional parameter and no output schema, the description covers the essential information: what it does, when the parameter matters, and a side-effect caveat. It does not detail the return format, but given the low complexity and presence of readOnlyHint, this is a minor gap rather than a deficiency.

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 0% schema description coverage, the description compensates by explaining that the optional course_id toggles between global grades (null) and a specific subject. This provides functional meaning to the parameter that the schema itself lacks, enabling correct invocation.

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 explicitly states the tool reads the user's own grades (global or per course) with the phrase 'Lee las calificaciones propias globales o de una materia'. It names the verb and resource precisely, and the scope (global vs. subject) differentiates it from related grade tools like get_quiz_best_grade without ambiguity.

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 description communicates when to use the tool (to read overall or per-course grades) and adds a key behavioral caveat ('no registra visita al informe'). However, it does not explicitly contrast with sibling tools or state when NOT to use it, so an agent must infer alternatives from the broader toolset.

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