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

With idempotentHint=true and destructiveHint=false provided by annotations, the description does not need to restate them. It adds value by disclosing server-side grading and the output format. No contradiction with annotations.

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?

The description is only two sentences, front-loaded with the core action. Every word contributes, with no repetition of schema information.

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?

Despite lacking an output schema, the description clearly states the return values. It also notes that grading can be done for partial answers, which is critical context. The tool has few params and is well-scoped, so this is complete.

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 documentation covers 100% of the parameters with descriptions, so the baseline is 3. The description does not add further parameter details, but none are needed.

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?

The description clearly states the verb 'Grade' and the resource 'quiz attempt', and specifies it returns per-question verdicts and an overall score. This effectively distinguishes it from sibling tools like start_practice_quiz, which initiates an attempt.

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?

It provides clear context for when to call ('once the user has answered'), but does not explicitly mention alternatives or when not to use it. The schema reference to 'quiz_id from start_practice_quiz' indirectly signals the workflow with a sibling tool.

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