benchmark

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

The annotations already establish read-only, idempotent, and non-destructive behavior, and the description does not contradict them. It adds useful context about loading scenarios and computing specific metrics, though it does not explicitly describe output or side effects beyond what the annotations imply.

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 two concise sentences with no redundant or filler content. It packs the core action, metrics, and default loading behavior efficiently.

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?

Given the simple schema and clear annotations, the description is adequate for an agent to understand what the tool does and what inputs it accepts. It could be slightly more explicit about return values or output format, but no output schema exists and the intended evaluation metrics are named.

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 single parameter has full schema coverage with a clear description ('Custom scenarios dir or file'). The tool description adds the useful default behavior (evals/scenarios/*.json), which clarifies how the parameter relates to the default when omitted.

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 ('Run') and resource ('eval harness'), and itemizes the metrics it produces. It distinguishes this tool from the memory- and workflow-related siblings by focusing on evaluation.

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 use for running evaluations and notes the default scenario path, but it does not explicitly state when to use this tool versus any alternative or provide conditions for when it should be avoided. There is no direct competing eval tool among siblings, but guidance is still minimal.

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