The Clearing — The Lantern & Consensual Agent Lab

preview_zero_pii_switchboard_scrub

Stateless dual-direction Zero-PII & base64-media scrubber preview showing exactly how inbound prompts and outbound operator replies are neutralized.

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": {
      "inbound_prompt": "<inbound_prompt>"
    },
    "name": "preview_zero_pii_switchboard_scrub"
  }
}

Input Schema

Name	Required	Description
`expects_json`	No	Whether the simulated caller set response_format json_object.
`inbound_prompt`	Yes	Sample inbound prompt or payload string to scrub.
`outbound_reply`	No	Optional sample operator reply to sanitize.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 14, 2026

TDQS

B3.4/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses two behavioral traits: the operation is stateless (no persistence) and dual-direction (inbound and outbound are both handled). It does not state that nothing is mutated, what the neutralization output looks like (placeholders, redaction markers, base64 media handling), or any limits, which matters for a preview tool with no output schema.

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?

It is a single front-loaded sentence with no filler or repetition. The only drag is dense nominal stacking ('Zero-PII & base64-media scrubber preview'), which costs a little readability without wasting length.

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

Completeness3/5

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

For a three-parameter preview tool with no annotations and no output schema, the description should convey what the preview returns and how scrubbing is represented. 'Showing exactly how ... are neutralized' gestures at the output but leaves the return shape and redaction semantics unspecified, which is the main gap for an agent deciding whether to call it.

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 description coverage is 100%, so all three parameters (inbound_prompt, outbound_reply, expects_json) are already documented in the schema. The description confirms the inbound/outbound duality but adds no format, size, or content guidance beyond what the schema supplies. Baseline 3 applies.

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 states a specific action (a stateless preview of a Zero-PII/base64-media scrub) over a specific resource (inbound prompts and outbound operator replies). It is clear that this is a demonstration of neutralization rather than the production scrubber, though the jargon ('switchboard', 'Zero-PII') adds fog. It does not name a sibling it is distinct from, but the purpose is legible.

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

Usage Guidelines3/5

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

The word 'preview' and 'stateless' imply a dry-run showing what scrubbing would do before applying it, but the description never states when to use this versus an actual sanitizer or an audit tool. No preconditions, exclusions, or alternatives are given; usage must be inferred.

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

All The Clearing — The Lantern & Consensual Agent Lab 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?