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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds useful non-structured context: 'Free', plus the fact that rows carry `prompt` and `requires` flags that must both be checked before rendering. It doesn't discuss pagination or result size, but the call-before-render contract is the behavior that actually matters here.

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, densely packed and front-loaded: purpose first, then parameter hint, then the usage imperative, then the row-contract warning. Slightly overstuffed with dashes and parentheticals, but every clause adds actionable information.

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 no output schema, the description must carry the return shape, and it does name the key row fields (`prompt`, `requires`) and the capability categories. It stops short of describing the full row structure (model names/ids, exact field names), which an agent would still have to discover empirically.

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% and the single `kind` enum is already documented with its default in the schema. 'Pass kind to switch between video, image and audio' restates the enum rather than adding format or edge-case detail, so the baseline 3 applies.

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 ('list the models you can generate with') and immediately enumerates what each row contains: reference image/video/audio counts and allowed resolution/duration/aspect values. An agent can distinguish this discovery tool from the render_* siblings without opening any 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 an explicit sequencing rule against the alternatives: 'Call this before any render so you pick settings that exist instead of guessing.' It also names the alternative family (render tools) and the condition (before calling a render tool) that selects it.

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