sanitize_pii

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

With no annotations, the description carries the full burden of behavior disclosure. It discloses the input (text) and the masking behavior for specific PII categories, but does not specify the output format, whether the entire text is returned, how masked placeholders look, or how toxicity filtering is handled despite being mentioned in the first sentence.

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 short sentences, front-loaded with the tool's core role and immediately followed by concrete PII examples and compliance purpose. No filler or redundant restatement of the tool name.

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 with no output schema, the description is largely sufficient: it tells an agent what input to provide and why. Minor gaps remain, such as the exact masking representation and whether non-PII text passes through unchanged, but these do not block correct invocation.

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 already describes the only parameter 'text' as 'Sensitive input text string to sanitize' with 100% coverage. The description adds context about what types of PII get masked, but does not add significant parameter-level detail beyond the schema, so the baseline score of 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?

The description clearly identifies the tool as a PII redactor that masks specific PII types (emails, phone numbers, credit card numbers, SSNs) from text, and positions it as a privacy/compliance safeguard for external LLM calls. This distinguishes it sharply from sibling text tools like extract_markdown or repair_json.

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 the contextual trigger: use this tool before sending data to external public LLMs, and names the compliance concerns it enforces (GDPR, HIPAA, DLP). It does not explicitly compare against alternatives or state when not to use it, but the use case is clear enough.

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