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

Annotations declare non-read-only, non-idempotent, non-destructive. The description adds rich behavioral context: asynchronous queueing, that the tool only acknowledges queuing, retrieval via get_ai_report, that re-running a section mid-build is safe, and that rebuilding an existing report doesn't count against the tariff limit. This goes well beyond annotations.

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 core purpose, then details sections, queueing, fetching, and quota. Four sentences, each contributing useful information. Slightly dense but no waste; could be trimmed marginally.

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?

Given no output schema, the description covers the essential async behavior, result retrieval tool, safety of repeated calls, and quota implications. An agent has all necessary context to invoke correctly and set expectations.

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 description coverage is 100%, so the schema already documents quiz_id, locale, and the section enum. The description adds some workflow nuance about sections being independent, but does not provide additional parameter syntax or formats. Baseline 3 is appropriate.

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: builds an AI report from survey answers. It further decomposes the report into three independent sections, distinguishing it from the retrieval sibling get_ai_report. An agent can tell exactly what this tool does.

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 outlines the workflow: use this to queue report generation, then fetch results with get_ai_report. Also notes that sections can be built independently and that repeated launches are safe, plus tariff constraints. No explicit 'when not to use' guidance, but the context is strong.

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