redact_by_entity

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

No annotations are provided, so the description carries the full burden. It discloses that processing is on-device, matches are best-effort pattern matching (not a completeness guarantee or compliance assessment), returns what was redacted plus an audit log, and that nothing is uploaded. This is rich, non-obvious behavioral context.

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 deliver all essential information: purpose, usage flow, alternatives, caveats, and privacy/upload behavior. The opening is front-loaded with the core action, and every clause earns its place without redundancy.

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 an output schema present, the description still explains what is returned ('what was redacted plus the audit log') and handles the tool's complexity: entity kinds, omit-all behavior, regional packs, review flow, and limitations. This is fully complete for a 5-param tool.

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 coverage is 100%, so baseline is 3. The description adds meaningful semantics beyond the schema: 'omit `kinds` to redact every kind detected' clarifies default behavior, and 'regions narrow to these regional packs (intersects with `kinds`)' explains the relationship between params. This rises above 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?

The description uses a specific verb+resource: 'Find and redact PII in a PDF in ONE on-device step' and clearly distinguishes this from sibling tools by framing it as the 'just scrub the obvious PII' shortcut. It explicitly contrasts with find_sensitive_regions, which is a strong differentiator.

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 states when to use this tool ('shortcut' for scrubbing obvious PII) and explicitly names an alternative: 'when you need to review before removing, call find_sensitive_regions first.' It also mentions the same caveat as the detector, giving clear context for suitability.

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