get_interaction

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

With no annotations, the description carries the full behavioral disclosure burden. It does add a key constraint ('Tree models only') and states that the tool returns SHAP interaction values, but it doesn't disclose prerequisites like having a loaded model, failure behavior for unsupported models, or the exact structure of the returned values.

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 core description is one short, front-loaded sentence that delivers the main idea. The parameter section is clear but partially redundant with the schema, which keeps it from being a 5.

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?

The tool appears to have an output schema, so little is needed about return values. However, the description is minimal for a tool with no annotations: it lacks preconditions, error behavior, and sibling distinctions. It is a borderline acceptable definition but could be much more helpful.

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, but it only restates the obvious: feature_a is the first feature and feature_b is the second. It doesn't explain where these names come from, expected format, or any relationship to model features, leaving the agent with little additional meaning over the schema.

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 uses a specific verb 'Return' and identifies a distinct resource: SHAP interaction values between two features, with the important 'Tree models only' limitation. This purpose is clear and sufficiently differentiates it from sibling tools like get_feature_importance and explain_prediction, though it doesn't name them.

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 explicit guidance on when to choose this tool over its siblings. 'Tree models only' is a precondition, not a usage selection criterion, and no alternatives or trade-offs are mentioned.

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