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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds valuable behavioral context beyond annotations: long-polling mechanics, the 1..8 batch limit, timeout default/max, and the poll_after_seconds retry hint.

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 concise sentences deliver the core behavior, limits, timeout semantics, and retry guidance with no filler. Key information is front-loaded with the action verb.

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 a simple polling tool with good annotations and only two parameters, the description covers purpose, limits, timeout, and follow-up calls. The absence of an output schema means the description could ideally clarify what 'terminal' looks like in the response, but this is a relatively minor gap.

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?

With 0% schema description coverage, the description must clarify the parameters. It does so by explaining the identifiers represent creations and that up to 8 can be polled, and by defining timeoutSeconds default and maximum. It does not explicitly label 'identifiers' as creation IDs, but the meaning is clear from context.

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 explicitly states the action ('Long-poll'), the resource ('creations'), the batch scope ('1..8'), and the completion condition ('until terminal or timeoutSeconds'). This clearly distinguishes it from sibling tools like magnific_creations_get or magnific_creations_list.

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?

The description implies the intended usage: call after starting creations to wait until they reach a terminal state, then use poll_after_seconds for follow-up calls. It does not explicitly name alternatives or state when not to use this tool, but the polling semantics are clear.

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