Detect and redact PII in text or JSON. Recognizers are pure pattern/checksum matching (regex + Luhn/mod-97/SSN-area validation) — no LLM calls, no external services. Person names and dates of birth are matched only via nearby context (e.g. 'Mr. Smith', 'DOB: ...'), not general NER, to keep false positives low.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | ||
| options | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so description carries full burden. It discloses internal mechanisms (regex, checksums) and context-based matching, but does not specify side effects (e.g., whether input is mutated or output format).
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 two sentences, immediately stating purpose and then adding relevant behavioral details. No redundant words, efficiently front-loaded.
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?
No output schema exists, but description does not hint at what the tool returns (e.g., redacted text, modified object). Also missing error handling or prerequisites. For a tool with nested options, more completeness would be expected.
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 0%, yet description provides almost no parameter details. It mentions 'text or JSON' for input but does not explain the flexible schema (anyOf), and completely ignores the options object with mode, locale, and entities.
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 states the tool detects and redacts PII in text or JSON, specifies recognizer mechanisms (regex, checksums, no LLM), and explains specific matching for names and DOB, making the purpose very clear and distinct.
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 explains the tool's limitations (pattern-based, no NER) which helps decide when not to use it. However, no sibling tools are provided for comparison, so it cannot differentiate from alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Only one tool exists, so there is no risk of confusion or misselection between tools.
With a single tool named 'redact', the naming is trivially consistent; there are no other tools to conflict.
A single tool covers the core PII redaction functionality, but for a server with this scope, separate detection and redaction tools might be expected, making it slightly thin.
The tool handles detection and redaction in one step, but lacks granular control over which PII types to redact or options for different input formats, so the surface is adequate but not comprehensive.