Agent Tools

pii_redact

Free tier: 25 calls/day per IP with header X-Free-Call: 1 (or ?free=1), then pay per call. Scrub text before it goes to a model or a log: JSON body {text, mask} (max 100,000 chars). Finds emails, phones, SSNs, cards (Luhn), IBANs, IPs, MAC addresses, API keys, JWTs, private keys, wallet addresses. mask is label, hash or star. Returns redacted text and counts. Not stored. Price $0.003 USDC per call via x402. Example output: {"redacted":"Contact [EMAIL] or [PHONE]. Card [CREDIT_CARD].","mask":"label","total_found":3,"counts":{"email":1,"phone":1,"credit_card":1},"findings":[{"type":"email","start":8,"end":20,"length":12}]}

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_redact"
  }
}

Input Schema

Name	Required	Description
`free`	No	Use the shared free allowance (25 successful calls per IP per UTC day across eligible tools). Defaults to false.
`mask`	No	label (default) [EMAIL], hash [EMAIL:ab12cd34], or star
`text`	Yes	Text to redact, max 100,000 characters

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 5, 2026

addedInput schema / properties / free

Added value: +{
+  "description": "Use the shared free allowance (25 successful calls per IP per UTC day across eligible tools). Defaults to false.",
+  "type": "boolean"
+}

AddedOct 28, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations, the description carries the full load and does so unusually well: it discloses the free-tier quota (25 calls/day per IP, X-Free-Call header or ?free=1), per-call price ($0.003 USDC via x402), the 100,000-character cap, that data is not stored, and the exact response shape with counts and character offsets. Nothing material about cost or side effects is left to inference.

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?

Dense but nearly every clause carries information an agent needs. The one structural flaw is ordering: pricing and free-tier mechanics lead the description, pushing the tool's actual purpose into the second sentence, so the most important content is not front-loaded.

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

Completeness5/5

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

Despite having no output schema, the description supplies a concrete sample response including the findings array with start/end offsets, so an agent knows exactly what comes back. Limits, storage behavior, and cost are all covered, leaving no material gap for a three-parameter redaction tool.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns extra by explaining the free-tier mechanism (header or query flag, shared per-IP daily allowance) that the schema only alludes to. Its 'mask is label, hash or star' sentence largely restates the enum, adding no new semantics.

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

Purpose5/5

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

States a specific verb and resource ('scrub text') followed by an enumeration of exactly what it detects (emails, phones, SSNs, cards with Luhn, IBANs, IPs, MACs, API keys, JWTs, private keys, wallet addresses). That detail distinguishes it cleanly from siblings like prompt_injection_check or manifest_scan, which also inspect text but for different threats.

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

Usage Guidelines4/5

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

'Scrub text before it goes to a model or a log' gives a clear situational trigger, and 'Not stored' addresses the obvious privacy objection. It does not name an alternative tool or state when not to use it (e.g. when you only need injection screening), so it stops short of explicit routing guidance.

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

All Agent Tools tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?