Skip to main content
Glama

Caelara Labs Agent Safety

pii_redactor

Redact emails, phones, SSNs, cards (Luhn), IPs, API keys and JWTs

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "pii_redactor"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesText to redact

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden, and it does add one genuinely behavioral detail: cards are validated with Luhn, so numbers failing the checksum are not redacted. However, it never says what the redacted output looks like (masking characters vs. typed placeholders), whether the original text is preserved, or how overlaps between entity types are resolved.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One short imperative sentence with the entity list front-loaded and the Luhn qualifier placed inline where it is needed. Nothing is redundant, though the fragmentary style gives no structure for an agent scanning for return-value or usage cues.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter, single-purpose tool this covers the essential scope of what gets redacted. The main remaining gap is return behavior: there is no output schema and the description does not state that it returns the redacted string, which is the one thing an agent most needs to chain it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter "text" is already documented as "Text to redact," so the schema does the work here. The description adds no constraints such as size limits, encoding expectations, or whether multiple documents can be passed. Baseline 3 applies when the schema is complete and the description adds nothing further.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ("Redact") and enumerates the exact entity classes handled: emails, phones, SSNs, cards, IPs, API keys, JWTs. That makes it clearly distinguishable from siblings like agent_output_validator or prompt_injection_scanner, which act on different concerns. It stops short of explicitly naming a sibling or stating scope limits, so it is not a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no statement of when NOT to use it, and no routing to alternatives such as agent_output_validator or prompt_injection_scanner. The agent must infer from the name and entity list that this is the redaction step in a pipeline rather than a detection/reporting tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources