nv_call

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 adds constraints like 'vision models only' for images and parameter ranges for temperature, but does not explain what happens on error, whether the call is synchronous, how output is returned, or any side effects. The lack of annotation coverage leaves significant behavioral transparency gaps.

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 compact and well-structured: a one-sentence purpose followed by a clear bulleted list of args. Every item adds necessary information without fluff, and the most important usage statement is front-loaded.

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 simple inference tool with an output schema, the description is largely complete: it covers all parameters and key constraints. However, it does not explicitly connect to nv_list_models for valid model IDs or explain how it differs from routing/auto tools, so there is a minor contextual gap.

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 0%, yet the description compensates thoroughly by explaining each parameter in plain language: model is an exact ID with an example, prompt is the user message, system is optional, images are URL/paths for vision models only, temperature has an explicit range, and max_tokens is a response cap. This adds rich meaning beyond the bare schema types.

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 states a specific verb ('Call') and resource ('one specific NVIDIA model'), clearly distinguishing it from sibling tools like nv_list_models (lists models) and nv_auto (likely automatic selection). The scope is precise and unambiguous.

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 'one specific NVIDIA model' implies that this tool is for direct, single-model calls when the exact model ID is known, but it does not explicitly mention alternatives or exclusion criteria. The description does not reference sibling tools or when to prefer nv_route or nv_auto, leaving usage guidance implicit.

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