nv_fanout

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. It explains the parallel execution, auto-selection via `task`, the max 6 models limit, and that images are for vision models only. It does not discuss failure modes or cost implications, but for a query-like fanout operation the disclosed traits are substantial and useful.

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 well-structured and front-loaded: a one-sentence purpose, followed by a concise use-case line, then a clean Args list. Every sentence adds value, and the length is appropriate given the need to document seven parameters that the schema leaves undescribed.

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?

The description covers all parameters, explains the two mutually complementary modes (`models` vs `task`), sets constraints (max 6, temperature range), and notes the vision-model limitation. Since an output schema exists, return value details are not required. The description is sufficiently complete for an agent to select and invoke the tool 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?

The schema provides no parameter descriptions (0% coverage), so the description's Args section is essential and does a thorough job. Each parameter is explained with practical constraints: `models` has max 6, `task` is used only when `models` is empty, `images` require vision models, `temperature` is 0.0-1.0, and `max_tokens` is a per-model cap. This significantly surpasses the bare 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 opens with a specific verb and resource: 'Run one prompt across several models in parallel and return every answer.' This clearly distinguishes it from sibling tools like nv_call (single model) or nv_route (routing), making the tool's unique fanout behavior immediately obvious.

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 provides explicit use cases: 'cross-check a hard question, compare model behaviour, or build a quick ensemble.' It also clarifies the choice between passing `models` explicitly or using `task` for auto-selection. However, it does not explicitly name alternative tools or state when not to use this tool, 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.