Scan for PII & Harmful Content

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds value by disclosing the response shape ('Returns findings and a redacted copy') and the redaction convention ([REDACTED]), which the annotations do not convey.

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?

Two sentences, zero filler: the detection scope comes first and the return behavior second. Nothing is redundant or padded.

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?

With no output schema, the description must carry return-value information, and it does so at least in outline ('findings and a redacted copy'), though it does not say what a 'finding' contains (type, spans, severity). For a simple 2-parameter tool this is nearly 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 both parameters are already documented at the field level. The description reinforces the redact behavior with the [REDACTED] placeholder, but adds no syntax, format, or edge-case meaning beyond the schema baseline.

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?

Specific verb ('Scan') plus resource ('text') with explicit enumerated detection categories (email, phone, SSN, credit card, IP; hate speech, violence, self-harm). No sibling is named for contrast, so the differentiation from rai_stream_scan or rai_pii_report is only implied by the 'single text' scope.

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?

There is no when-to-use guidance, no prerequisites, and no alternatives named among the many rai_* siblings that overlap (rai_pii_report, rai_stream_scan, rai_policy_check). The agent must infer usage entirely from the verb 'Scan'.

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