Evaluate Demographic Bias

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds meaningful behavioral detail by disclosing the output structure (per-probe scores with a 0-1 scale, confidence intervals, intersectional amplification, overall grade), which matters since no output schema exists.

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, front-loaded with the verb and the six dimensions, then the input expectation, then the outputs. No wasted phrasing.

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?

Despite using a nested input object, the definition covers purpose, required inputs, and return values (compensating for the absent output schema), and annotations carry the safety profile. Only the lack of explicit sibling routing keeps it short of complete.

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 100%, so the schema already documents all four parameters. The description reinforces the probe_responses concept with 'paired response samples,' but adds little syntax or format beyond what the schema provides; baseline 3 is appropriate.

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?

States a specific verb (Evaluate) and resource (demographic bias) and enumerates the six probe dimensions it covers (gender, racial, age, religious, occupational, cultural). This is distinctive enough among the rai_ siblings that an agent can identify it without opening the schema.

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 instruction to 'provide paired response samples for each demographic group' implies how to prepare input, but there is no explicit when-to-use guidance, no when-not-to, and no routing to alternatives like rai_redteam_analyze or rai_scan. Usage is implied rather than stated.

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