check_bias

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

With no annotations provided, the description carries the burden. It discloses that class-balance and chi-square always run regardless of parameters, that disparate impact only runs when both optional params are supplied, and notes the output size is small. This is useful behavioral context beyond a simple summary.

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?

Three sentences with no fluff. The opening line summarizes the three checks, then the following sentences give precise conditions and output size. Every line adds value.

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 has an output schema, so return format details are not needed. The description covers what checks run, when they run, and the output size. It omits error conditions or data type prerequisites, but for a 3-parameter check tool this is adequate.

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 explains the role of outcome_column and protected_attributes in triggering disparate impact, and implicitly defines source_id as the data source. The '2-20 cardinality cats' detail adds context for the class-balance check.

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 defines the tool as running three bias checks: class imbalance, sampling bias, and conditional disparate impact. It names specific statistical methods (chi-square, 80% rule) and distinguishes from siblings by focusing specifically on bias rather than general quality or distribution checks.

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?

It states that class-balance and sampling bias always run, while disparate impact requires both outcome_column and protected_attributes. This gives clear conditional guidance, though it doesn't explicitly contrast with alternative check_* tools. The conditions imply when the tool is relevant.

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