save_quiz_attempt_responses

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

Annotations already flag this as a non-readonly, destructive, non-idempotent write, so the description's job is to add context and it does: it clarifies answers remain editable ('can still be changed later'), which tempers the destructiveHint, and it volunteers that the behavior is UNVERIFIED against a real quiz. It doesn't say whether re-saving the same page replaces or merges with earlier responses, which is the main behavioral gap for a non-idempotent write.

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 short blocks, front-loaded with the differentiating clause before the confirmation protocol. Slightly redundant since the dry_run default is repeated in the schema, but nothing is padded out.

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?

An output schema exists, so return values needn't be explained, and the description covers the one non-obvious thing an agent must do (two-phase dry-run confirmation). It stops short of explaining how this call relates to the finalize step or what happens if the save fails mid-attempt, but for a 4-parameter tool it is largely 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 coverage is 100%, so all four parameters (including dry_run and the responses map) are already documented, and the description largely restates the dry_run semantics. It adds no new syntax or format guidance for the `responses` object beyond what the schema's own description covers. Baseline 3 applies when the schema carries the load.

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 (save quiz attempt responses) and immediately bounds the scope with 'WITHOUT finishing the attempt', which is exactly the line separating it from process_quiz_attempt. An agent can tell from the first line whether this is the right call or whether it should finalize instead.

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?

Gives an explicit, actionable protocol: call with dry_run=True first, show the preview to the user, then re-call with dry_run=False only after explicit confirmation. What's missing is naming the alternative (process_quiz_attempt) for the 'finish the attempt' case, so the agent has to infer the hand-off from context rather than read it.

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