rush_ai-eval

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

No annotations are provided, so the description carries the full burden for behavioral disclosure. It does reveal a permission requirement for live inference, but it does not describe side effects, what path refers to, or what happens when permissions are missing.

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?

Two sentences with no filler: the purpose is front-loaded, and the permission caveat is placed immediately after. Every word earns its place.

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 8 parameters, no annotations, and no parameter descriptions, an agent cannot confidently determine what path should contain or which allow flags are required for a given run. The output schema helps with return values but does not compensate for the missing operational context.

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 description coverage is 0%, so the description must compensate for undocumented parameters. It vaguely relates to the allow_* flags by mentioning explicit permissions, but it never explains path, allow_slow, allow_browser, or any other parameter's role.

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 action ('Evaluate') with concrete objects ('LLM prompts, agent workflows, and safety guardrails'), which clearly communicates what the tool does. It distinguishes itself from the general lint/test/review siblings, though it does not explicitly contrast with related AI-focused siblings.

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 only guidance is 'Requires explicit permissions for live inference runs,' which is a prerequisite rather than a usage guideline. There is no indication of when to prefer this tool over alternatives like rush_review or rush_hallu_guard, and no exclusion criteria.

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