return_owned_exam_question

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

With no annotations, the description carries the full burden; it does convey one important behavioral fact — that leaving the preview does NOT submit anything, so this is a non-destructive escape path. It omits state dependencies ('observed' implies the link must already be visible in a prior observation), what happens to unsaved answers, and what state the session is left in afterwards.

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?

A single short sentence with no filler, and the key qualifier ('without submitting') is placed where it will be read. The phrasing is slightly awkward ('Use the observed Return link to leave full preview') but nothing is wasted.

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 zero-parameter, no-output, no-annotation tool the description is minimally sufficient — an agent knows it navigates out of a preview without submitting. It is still too thin on the surrounding state machine (what must be true before calling, and what the agent should do next) to be considered 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?

The tool takes zero parameters, so the baseline of 4 applies; there is nothing for the description to document beyond the implicit dependency on prior browser observation, which is only hinted at by the word 'observed'.

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 states an action ('leave full preview without submitting') via a specific mechanism ('the observed Return link'), which tells the agent this is a navigation/exit operation rather than a read or write. However, terms like 'full preview' and 'Return link' are tool-specific jargon not defined anywhere, and nothing distinguishes it from close cousins such as preview_owned_exam_questions or inspect_owned_exam_navigation.

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: call this when you are inside a full preview and want to back out without submitting answers. There is no explicit statement of preconditions (e.g., that a preview must already be open, or that the Return link must have been observed first) and no named alternatives for other ways of leaving the preview.

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