data_data_anonymizer

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

Beyond the annotations (readOnlyHint, destructiveHint, idempotentHint), the description discloses critical behavioral traits: regex-based detection with validity checks, a specific resolution order for longer/stricter patterns to avoid partial matches, local execution without external services, rate limits (60 req/min for anonymous), and return format (masked text, replacement list, match counts). This fully informs the agent about how the tool behaves.

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?

The description is dense yet concise, front-loading purpose and detected types, then transitioning to usage guidance and technical details. Every sentence contributes meaningful information without redundancy. It is well-structured for an AI agent to quickly parse.

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?

Given the tool's moderate complexity (3 parameters, output schema present), the description covers all essential aspects: purpose, usage context, detection details, operational constraints, and return format. The annotations further complete the behavioral profile, making the tool fully comprehensible.

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 input schema has 100% coverage, so the description's parameter details are supplementary. It clearly explains each mask mode (token, partial, counter) with examples, and describes the enable object's default behavior (all types on). This adds value beyond the schema's descriptions, though the schema already provides formal definitions.

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 Data Anonymizer and Redactor, lists specific PII types detected, and explicitly distinguishes itself from the sibling tool 'data_data_faker' which generates new synthetic data rather than masking existing values.

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 provides explicit guidance on when to use this tool ('scrub or redact real PII from logs, tickets, or datasets') and when to use the alternative ('data_data_faker' for generating synthetic test data). It also notes that the tool runs locally, is read-only, non-destructive, deterministic, and rate-limited, giving the agent clear operational context.

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