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

While annotations handle safety and predictability, the description provides crucial behavioral context by specifying the exact metrics returned, including 'VRAM' and 'live cheapest on-demand price (USD per GPU-hour)'. This informs the agent about the quality and structure of the data it will receive.

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 a single, punchy sentence that avoids filler. It front-loads the core function and necessary details, ensuring every word adds value.

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 zero-parameter listing tool, the description is highly complete as it defines the source, the resource scope, and the detailed content of the result. The agent has all the necessary information to understand the scope and utility of the function.

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?

Since there are zero parameters, the description successfully adds semantic value by detailing the specific output attributes (VRAM, price, and provider count) that an agent would need to parse the resulting data effectively. This compensates well for the lack of input structure.

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 is highly specific, clearly stating that the tool lists GPU families, and detailing exactly what data points (VRAM, live price, provider count) are included. It clearly defines the resource and its scope, effectively differentiating it from tools like `find_model`.

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 does not explicitly state when this broad list should be used versus a more targeted tool from the sibling set, such as `cheapest_gpu`. However, since it is a comprehensive list, its usage context is fairly implied as a general information gathering step.

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