create_evaluation

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

No annotations are provided, so the description must cover behavioral traits. It implies a run action but doesn't disclose side effects like cost, asynchronous behavior, or resource usage. The description is too brief for a tool with no annotations.

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 sentences long, with the purpose front-loaded. Every sentence adds meaningful information without redundancy or fluff.

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 schema covers all parameters and there is no output schema, the description provides an adequate but minimal overview. It could be more complete by noting return values or asynchronous behavior, but it suffices for a straightforward creation tool.

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 input schema already describes all parameters with 100% coverage. The description adds value by referencing list_evaluators for available evaluators and clarifying that either user_model_id or base_model is required (though this contradicts the schema's optionality). This extra context helps the agent.

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 creates a new model evaluation and explains the process (running a model against a dataset with evaluators). It distinguishes itself from sibling tools like list_evaluators and show_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 mentions using list_evaluators to find available evaluators, which provides some guidance. However, it doesn't explicitly state when not to use this tool, such as when to use estimate_evaluation instead, or clarify the choice between user_model_id and base_model.

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