nv_auto

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

With no annotations, the description carries the full burden of behavioral disclosure, but it only mentions the auto-selection and the vision-model forcing for images. It does not state whether the tool is a read-only generation operation, any side effects, or what the response contains. The description lacks important safety and operational details such as cost, latency, or error behavior.

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?

The description is efficient and front-loaded. The first sentence immediately states the core purpose, followed by a concise parameter list with short, focused definitions. No sentence is wasted, and the structure is easy to scan.

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?

Despite having no annotations, the description covers the essential input parameters and the primary behavior. Since an output schema exists, it need not explain return values. It does not address edge cases (e.g., unsupported tasks) or selection criteria, but for a straightforward auto-selection tool, it provides enough context for correct invocation.

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?

The schema has 0% description coverage, so the tool description must compensate. It explains every parameter, adding meaningful details: 'task' has examples, 'images' notes it forces a vision model, 'temperature' gives a range, and 'max_tokens' is described as a response cap. Some descriptions are redundant (e.g., 'prompt: the actual content to send'), but overall it provides useful 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?

The description clearly states the tool's purpose with a specific verb ('Pick') and resource ('best model for the task'), then notes it runs the prompt on that model. This distinguishes it from siblings like nv_call (which likely uses a specified model) and nv_route (which may route based on rules). The phrase 'automatically' adds a unique behavioral trait.

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 usage when automatic model selection is desired, but it does not explicitly state when to use this tool versus alternatives like nv_call or nv_route. There are no exclusions or conditions, leaving the agent to infer the appropriate context. The phrase 'automatically' gives some clear context but falls short of explicit guidance.

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