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

Annotations say readOnlyHint=false and idempotentHint=true, but the description supplies the reasoning and side effects the annotations cannot: the result is persisted with the exercise attempt and only one evaluation is allowed per exercise. It also discloses the return payload (correct count, which ones, solution plus short explanation, listening transcript) and the auth scope, all beyond structured fields.

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?

Front-loaded with the action and the source of attempt_id, and most sentences carry new information (persistence, auth scope, return contents). It runs long and repeats the 'never guess answers' rule already present in the answers parameter description, which is the only real waste.

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 an output schema present, return values need only light framing, and the description goes further by naming what comes back and noting the listening transcript. Prerequisites, auth behavior, side effects and the one-evaluation rule are all covered; nothing needed to call it correctly is missing.

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%, so the baseline is 3. The description restates the answer format ('task number and letter; for marking tasks the numbers of the marked entries') rather than adding syntax or edge cases beyond the schema, and it does not mention the optional feedback_language parameter at all.

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 ('check the user's answers to an exercise') and anchors it to the sibling that produces the required identifier ('from get_practice_exercise, using its attempt_id'). An agent can distinguish it from evaluate_text, get_evaluation_result and get_practice_exercise 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?

Explicit prerequisites and alternatives are given: must come from get_practice_exercise with its attempt_id, one evaluation per exercise, works with or without sign-in, and only the caller's own exercises are checkable. It also gives a strong negative instruction ('Never fill in, guess or correct answers for the user'), which is exactly the failure mode an agent would otherwise fall into.

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