Grades

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds a real behavioral trait beyond that: results are truncated at 30 and are limited to the newest progress-dossier entries, which tells the agent to expect partial data. It stops short of saying whether the averages are computed over the capped set or the full set.

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?

One front-loaded sentence establishes what it returns, then a single routing sentence covers all four alternatives. No filler, no repetition of the tool name as content.

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?

No output schema exists, so the description must describe the return value — and it does, naming both the capped result list and the per-subject averages. The only remaining ambiguity is the statistical scope of those averages, which is a minor gap for a summary tool.

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 description coverage is 100% and the single leerlingId parameter is documented there, including the multi-child requirement. The description adds nothing about the parameter, so this sits at the baseline the schema coverage earns.

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 ('Quick grade summary') plus the exact content returned: newest progress-dossier results capped at 30 and per-subject averages. The limits ('capped at 30', 'per subject') let an agent distinguish it from the four named sibling grade tools without opening any schema.

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?

Explicitly routes to alternatives with the condition that selects each: grades_latest for more or exam results, grades_overview for a full school year, subject_grades for one subject in depth, exam_grades for the PTA/SE dossier. Both when-to-use and when-to-use-something-else are stated.

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