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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds the fixed 30-day lookback window, which is genuinely useful behavioural context, but says nothing about pagination, whether all students are returned or only active ones, or what a zero-activity student looks like in the result.

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?

Two short sentences: what it returns, then when to use it. Front-loaded with the payload and the time window, with no 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?

With no parameters and no output schema, the description carries the full burden of conveying the return shape for a 50-plus-sibling read API. It hints at the shape (per-student day counts) but leaves ambiguous whether the value is a numeric count or a list of dates, and whether inactive students appear at all.

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?

There are zero input parameters, so the baseline applies. The mention of "by student_id" is useful not as a parameter but as a statement about how results are keyed, compensating slightly for the absent output schema.

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?

"Days each student trained in the last 30 days, by student_id" gives a specific metric, a fixed time window, and a grouping key, so the agent knows exactly what is produced. It does not explicitly differentiate itself from neighbours like get_student_summary or get_student_health, which is why it falls short of a 5.

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?

"Use it to find students who stopped training" supplies one concrete scenario, which is more than nothing. However, no exclusions or alternatives are named among many closely related read tools (get_student_summary, list_students, get_student), so the routing decision is left to inference.

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