rush_ai_eval

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

With no annotations, the description carries the full burden. It adds one behavioral detail (permissions for live inference runs) but does not disclose side effects, what the evaluation does with the path, or the implications of the allow_* flags. This is minimal disclosure for a potentially impactful tool.

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 brief, front-loaded with the action, and has no redundant words. However, it is so short that it omits crucial context, so it is concise but not optimally structured for completeness.

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 tool with 8 parameters, 0% schema coverage, and no annotations, the description is severely incomplete. It does not explain what 'path' points to, what each allow flag controls, when to use this tool versus siblings, or how the evaluation is performed. The output schema does not compensate for the missing parameter and usage details.

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%, and the description does not explain any of the 8 parameters. The required 'path' parameter is undefined, and the boolean allow_* flags (allow_slow, allow_build, allow_browser, etc.) are entirely unexplained, leaving the agent without semantic guidance.

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 clear action ('Evaluate') and identifies specific target resources: LLM prompts, agent workflows, and safety guardrails. It does not explicitly differentiate from overlapping siblings like rush_prompt_eval, but the purpose is clear enough to distinguish from generic tools.

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 provides no guidance on when to use this tool versus alternatives. 'Requires explicit permissions for live inference runs' is a prerequisite, not a usage criterion, and no sibling tools are mentioned for comparison.

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