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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds that the response is a capability manifest of accepted values, which is useful context, but it says nothing about the odd idempotentHint=false on a read tool or about error behavior for an invalid model key.

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?

A single front-loaded sentence with no filler; the enumerated capability list is dense and immediately useful for deciding whether to call it.

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 one-parameter read tool with annotations and an output schema, the description covers the essential question (what does it tell me about a model). It could go slightly further by stating it must be called before generating with an unfamiliar model, but nothing critical 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?

With schema description coverage at 100% and one required parameter fully documented as 'model key from list_models', the baseline of 3 applies. The description never mentions the model parameter, adding no semantics beyond 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?

Specific verb (Get) plus resource (a model's accepted settings) with an enumerated payload (durations, aspect ratios, resolutions, image modes/limits, audio support). An agent can tell this apart from list_models, but there is no explicit statement distinguishing it from settings_read or pick_model beyond the 'model' framing.

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?

No explicit when-to-use or when-not language; the guidance is implied (inspect a model's valid parameters before calling generate_video/generate_image). The only routing hint, 'model key from list_models', lives in the schema rather than the description.

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