detect_bias

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

No annotations are provided, so the description must carry the burden. It implies a read-only detection tool but does not explicitly state whether data is modified, if authentication is required, or if there are any side effects. The description lacks behavioral details such as performance constraints or assumptions about the data.

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: the first states purpose and method, the second states output. It is front-loaded, efficient, and contains no redundancy. Every word 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?

Given no output schema and no annotations, the description is incomplete. It does not detail the format or structure of the returned disparity ratios and bias risk label, nor does it explain the required shape of the input records (e.g., expected fields). For an analytical tool, this leaves ambiguity for the agent.

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 schema covers 100% of parameters with descriptions, so the baseline is 3. The description adds context by mentioning comparison of approval rates, amounts, and distributions, which aligns with group_field, outcome_field, and outcome_type. However, it does not add significant meaning beyond the schema, and the relationship between parameters is only implied.

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 detects demographic or categorical bias in financial datasets, specifying the method (comparing approval rates, average amounts, outcome distributions) and output (disparity ratios and bias risk label). It is a specific verb+resource combination that distinguishes it from sibling tools like audit_data_quality or evaluate_model_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?

The description does not provide guidance on when to use this tool versus alternatives, nor does it mention prerequisites or exclusions. For example, it does not state that this tool is appropriate when exploring fairness or that it should not be used for non-categorical attributes. No explicit context is given for use cases.

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