Privacy sanitizer (feature #7)

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

With no annotations provided, the description carries the behavioral burden. It meaningfully discloses that masking happens locally and prior to external model calls, which is a key privacy-relevant behavior. It does not discuss reversibility, side effects, or the exact output shape, but the local-processing guarantee is strong 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?

One dense sentence front-loads the action ('Mask PII and secrets'), follows with a useful categorized list, and ends with the placement ('locally before...external model'). There is no filler; every clause adds information.

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?

For a single-parameter tool, the description is nearly complete: it states what the tool processes, which categories it handles, and when it should be used. The main gap is that the return value is only implied as masked text and is not explicit, with no output schema to compensate.

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% and the only parameter, 'text', is already described as 'Text to sanitize.' The description's list of recognized PII categories adds operational context but does not add parameter-level constraints such as format, length, or encoding expectations.

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 opens with the verb 'Mask' and clearly identifies the resource: PII and secrets, enumerating concrete categories like emails, cards, IBAN, and API keys. It is specific and meaningful, but it does not explicitly contrast itself with sibling tools such as jev_guardrail or jev_redteam, so it stops short of full sibling differentiation.

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?

'before anything is sent to an external model' gives an explicit triggering context, and 'locally' adds a clear privacy constraint. The description does not name alternatives or state when not to use the tool, but the usage timing is specific enough to guide an agent.

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