benchmark

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

With no annotations, the description fully discloses that the tool is 'HEAVY', consumes compute, and may load the model. This provides essential behavioral context an agent needs to decide invocation.

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?

Three sentences, each adding unique value: purpose, heaviness warning, and provider behavior. No redundant information.

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 explains inputs and output metrics (latency, throughput) with units. However, lacking an output schema, it could have specified the exact return format or structure. Still, it provides sufficient context for an agent.

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?

While the schema has 100% coverage, the description adds meaning by explaining that prompt is optional with a default, and that maxTokens defaults to 64. It also contextualizes the tool's use of these parameters in benchmarking.

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 performs a benchmark by running real inference, measuring latency and throughput. It specifies verb 'Runs' and resource 'inference', and distinguishes from sibling tools (e.g., list_models, complete) which serve different purposes.

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 mentions behavior without a provider argument but does not explicitly state when to use this tool vs alternatives. It lacks guidance on when not to use it, though sibling tools are clearly different.

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