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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so restating 'Read-only' is redundant. What the description adds beyond structured data is the security-sensitive disclosure that the quizmaster link is private and must never be surfaced to players, which is a real behavioral constraint an agent could otherwise violate. It does not describe the shape of the returned links (URL vs. embedded image data).

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?

One front-loaded sentence with parenthetical audience labels for each link type. Every clause carries distinct information: no filler, no repetition of the title, and the most safety-critical element (the private quizmaster link) is stated last with emphasis.

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 no output schema, the description correctly compensates by enumerating what the tool returns, which is exactly the missing structured information. The remaining gap is format ambiguity: 'QR image' could be a URL, a base64 payload, or a rendered asset, and the description does not say. Otherwise complete for a single-parameter read.

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?

There is a single parameter with 100% schema description coverage; the schema already states that quiz_id comes from create_quiz or list_quizzes. The description adds nothing about the parameter, neither its format nor its provenance. Baseline 3 is correct when the schema carries the full burden.

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 names the resource precisely (the quiz's test and live game links) and enumerates the individual link types returned: player join link, QR image, projector screen, and quizmaster link. An agent can immediately tell this is not get_quiz or get_access. It stops short of explicitly contrasting itself with the nearest siblings, which keeps it at 4 rather than 5.

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 supplies clear usage context by mapping each link to its audience: player join link and QR are to share with players, and the quizmaster link is 'only for the maker, never for players'. That is actionable guidance for a downstream agent assembling a response. However, it gives no explicit 'use this instead of X' routing against siblings such as get_access or get_quiz.

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