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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuine value beyond them by disclosing the shape of returned data: video duration is an enum per model (durations_seconds), not a min-max range — a trait an agent would otherwise guess 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?

Two sentences, both front-loaded: the first states the purpose, the second immediately delivers the non-obvious durations_seconds caveat. No 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?

An output schema exists, so return values needn't be described in full, yet the description includes the one detail most likely to cause misuse (duration enum vs range). For a single-enum-param read tool, nothing an agent needs to call 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?

There is only one parameter (kind), and schema description coverage is 100% with a full enum of allowed kinds. The description adds no meaning to the 'kind' parameter itself, so the baseline 3 applies; the durations_seconds note pertains to output, not this parameter.

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 (List) and resource (models, defaults, limits, credit costs) scoped to 'one generation kind before queueing it'. An agent can distinguish it from the generation_*_create siblings, which consume the options this tool returns.

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 phrase 'before queueing it' clearly signals this is a pre-flight/discovery call that precedes a generation create. It does not explicitly name the alternative tools (generation_image_create, generation_video_create, etc.), but the sequencing intent is unambiguous.

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