check

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

With no annotations at all, the description carries the full burden, and it delivers several non-obvious facts: hidden tests reveal only pass/fail, quizzes are graded only after every question is answered, and only the first check of a quiz is recorded (a meaningful idempotency-like constraint). It omits the key prerequisite of whether unsaved code is graded and does not say what side effects 'record the attempt' has on progress state.

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 sentences, front-loaded with the core action, followed by the constraining edge cases. Every clause conveys a distinct rule; nothing is redundant or repeated from structured fields.

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 single-optional-parameter tool with no output schema and no annotations, the description covers the action, the grading semantics, and the quiz edge cases, including partial return-value information (pass/fail only). The main remaining gap is the save-before-check prerequisite, which an agent would need in order to call this correctly.

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?

One optional parameter with 100% schema description coverage, so the schema already explains that slug identifies the exercise and defaults to the current one. The phrase 'current code' and the implicit default-to-current behavior add no meaning beyond what the schema states; baseline 3 applies.

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: 'Grade the learner's current code against all tests and record the attempt.' An agent immediately knows this is an evaluation/grading action distinct from saving. It stops short of differentiating from save_exercise, which is the closest sibling and is not mentioned, so the boundary between checking and saving must be inferred.

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?

Usage is implied by the phrase 'current code' and the quiz condition, but there is no explicit statement of when to call this versus save_exercise, nor whether code must be saved first. The quiz rule ('graded once every question is answered') is a genuine gating condition that helps, but it is the only routing-style guidance present.

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