preview_quiz

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

Annotations already flag readOnly=false, destructive=false, and the description adds context beyond them: no account/login/API key required, the tool consumes a finished JSON and nothing else, and the output is a browser-openable share link. It does not detail side effects beyond creation, but the preview/try-out framing plus existing annotations cover the safety profile.

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 tight paragraphs: the first front-loads purpose and sibling disambiguation, the second covers the input contract and prerequisite. Minor redundancy between the appositive description of a graded quiz and the later 'graded quiz... with correct answers and a final score' phrase keeps it just short of flawless.

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 and a single nested object parameter, the description covers everything needed: purpose, use cases, alternatives, prerequisite, auth requirements, and input shape pointer. No material gap remains for an agent to call it correctly.

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% for the single 'form' object, and the schema itself documents the shape source (preview_guide) and the forced 'scene' value. The description reinforces this with 'takes the finished assessment JSON and nothing else,' which clarifies that the parameter must be the complete, ready-to-use artifact.

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 outcome — 'Create a shareable RooQuiz preview quiz... and get a link to open in the browser' — with the grading model spelled out (right/wrong, points, score). It also names the sibling skills it is not (preview-scorecard, preview-outcome), so an agent can reliably tell the three preview tools apart.

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 explicit when-to-use criteria ('when someone wants to build, try out, or share a graded quiz, test, trivia, or exam'), names the two alternatives with their distinguishing conditions, and states the prerequisite to call preview_guide with type 'quiz' when the schema isn't already in context.

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