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

Goes far beyond the annotations: the call returns immediately with an ID and enqueues work, the quiz starts empty, readiness is polled via the same tool returning pending/ready, and synchronous assembly was deliberately removed due to ~1 minute model calls timeouts. This is exactly the async contract an agent needs and the annotations (readOnly=false, destructive=false) do not convey.

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?

Four sentences, front-loaded with what it does, then the async behavior and readiness polling. The closing rationale about timeouts earns its place by explaining behavior. Slightly dense but no wasted filler.

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 an async, dual-mode tool with no output schema, the description fully covers the return contract (ID on start, pending/ready on poll) and the sequencing the agent must follow. Nothing needed to invoke it correctly is missing.

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 baseline is 3, but the description adds real meaning: quiz_id is not just an ID but the polling key, and it explains the mutually exclusive create-vs-poll usage of prompt/folder_id versus quiz_id. That contextualizes the parameters beyond their individual schema descriptions.

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+resource: it assembles a quiz from a text description, and clarifies this is background/async generation rather than a manual build. This distinguishes it well from a plain create_quiz conceptually, though it never names create_quiz or create_quiz_from_template as explicit alternatives.

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?

Clearly establishes the two modes of use: call to start generation, then call again with quiz_id to poll readiness. It also explains why there is no synchronous path (model latency/timeouts). It stops short of telling the agent when to prefer this over create_quiz or create_quiz_from_template.

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