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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds two things they don't: "Does not record anything" (no persistence side effect) and the full return payload, which matters because there is no output schema. Not a 5 because it never explains whether submitting `confidence` changes subsequent behavior or how the blind-spot signal is consumed.

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?

Three short sentences, front-loaded with the invocation trigger, then the return contract. "A confident wrong answer is a blind spot" is the only sentence with questionable necessity, though it does hint at the confidence parameter's purpose.

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?

Return values and non-persistence are covered, which is the important gap given no output schema, and the read-only annotations carry the safety profile. However, for a 4-parameter tool with two undocumented parameters and no output schema, the description should still clarify what `confidence` and `questionId` mean and how they are used.

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 coverage is only 50%: `answer` and `program` are documented in the schema, but `questionId` has no description and `confidence` carries only an enum. The description never mentions any parameter, offering at most a cryptic nudge ("A confident wrong answer is a blind spot") without explaining that confidence is an optional input or what it affects.

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?

Specific verb and resource ("Check practice answer" for "a CertArc practice question") plus a stated return payload: correctness, correct option, and per-option explanations. The trigger condition ("the learner has chosen an answer") implicitly separates it from practice_question, but no sibling is named, so the differentiation is inferential rather than explicit.

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 this when the learner has chosen an answer" gives a clear, unambiguous invocation condition. It stops short of naming alternatives or exclusions (e.g. use practice_question to fetch a question, get_result_review for post-hoc review), leaving the boundary for the agent to infer.

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