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

Annotations say readOnlyHint=false and idempotentHint=false but say nothing about cost or lifecycle. The description adds the two most decision-relevant behaviors: it spends credits and returns a queued (asynchronous) prediction that must be polled. Auth requirements and failure semantics are left implicit.

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?

Three sentences, front-loaded with the purpose before constraints, async flow, and the retry variant. The output summary sentence is slightly redundant given the output schema, but overall it is dense without waste.

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 an output schema present, return values need not be explained, yet the description still gestures at them. The async/polling lifecycle, credit cost, input constraints, and retry path together give an agent everything needed to invoke this and follow up correctly.

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 0%, so the description must carry parameter meaning and largely does: it maps `reference` to "a finished clip or a video upload" and explains `retry_prediction_id` as the way to re-run a failed prediction on the same video. It does not spell out the type/id structure of the reference object, but that structure is visible in the schema.

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 ("Score how a short video is likely to perform") and names the outputs it produces. It also differentiates itself from the sibling get_virality_prediction by framing that tool as the polling endpoint, so an agent can place this call without opening either schema.

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?

Gives concrete usage context: a finished clip or an upload, up to sixty seconds, and explicitly routes the agent to poll get_virality_prediction until status is ready or failed. It also names the alternative path (retry_prediction_id instead of a reference). There is no explicit when-not-to-use statement, so it falls just short of a 5.

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