run_fgsm

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

With no annotations, the description carries full burden. It discloses the batch cap (100 samples), return metrics, and clarifies a common misconception about plausibility rate. However, it does not state whether the tool modifies the model, requires authentication, or has other side effects.

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 compact with three sentences, each serving a purpose: stating the action, capping batch, and explaining return values. It is well-structured and front-loaded.

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 5 parameters, no output schema, and no parameter descriptions in the schema, the description omits critical details about seed, epsilon, n_lime_samples, and model registration requirements. This leaves the agent underinformed for correct invocation.

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. It only describes the batch parameter (cap) and implicitly mentions epsilon via the attack name. Other parameters (seed, model_handle, n_lime_samples, epsilon) are left unexplained, leaving the agent without sufficient understanding.

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 opens with a specific verb and resource: 'Run a LIME-guided FGSM adversarial attack against a registered model.' This clearly states what the tool does and differentiates it from sibling tools like run_boundary_attack or run_membership_inference.

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?

No explicit guidance on when to use this tool versus alternatives like run_boundary_attack. The description does not mention prerequisites or scenarios where this attack is appropriate.

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