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

Annotations only declare the write/safety profile; the description adds real context beyond them: the return value (a playable/shareable link), the play modes, and that Tjaz validates the quiz against its terms before saving. It does not mention duplicate handling or that repeated calls create separate quizzes (non-idempotent), which is the one behavioral trait an agent could still get wrong.

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?

Front-loaded with the action and outcome, then the usage trigger, then the validation caveat — a sensible order. The opening sentence runs long with three embedded clauses and could be split, but nothing is redundant.

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-value detail is optional, yet the description still tells the agent a link comes back and what it is for. Combined with the terms-validation note, an agent has everything needed to call this correctly for a 5-parameter write tool.

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 80% and the schema already documents title, public, players, language, and the nested question shape in detail. The description adds no parameter-level meaning of its own beyond restating that questions are multiple-choice, so the baseline 3 applies.

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 ('Saves a multiple-choice quiz ... on Tjaz') plus the result ('gives back a link to play it alone, in a 3D game or together on a big screen'). It gestures at a distinction from make_quiz via 'whose questions are already written', but then adds 'or asks you to write them', which blurs that boundary rather than sharpening it.

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?

'Use this when the user has the questions, e.g. pasted them, or asks you to write them' gives a clear trigger condition. However, no alternative is named, so an agent facing a sibling like make_quiz or find_quizzes gets no routing guidance and must infer the split, which the ambiguous 'or asks you to write them' makes harder.

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