Skip to main content
Glama
privacyscrubber-mcp

privacyscrubber-mcp

Restore Cleartext from Surrogate Tokens (ZTDS RFC v1.0)

ztds_restore
Read-onlyIdempotent

Rehydrates surrogate tokens back into original cleartext using the local in-memory session table, without modifying or deleting the session.

Instructions

Drop-in ZTDS RFC v1.0 restoration tool. Rehydrates surrogate tokens back into original cleartext using the local in-memory session table without modifying or deleting the session.

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": "ztds_restore"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesUTF-8 text or LLM response containing surrogate tokens to restore.
sessionIdNoOptional session identifier matching the session passed to ztds_sanitize. Defaults to 'default'.default

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.5.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnly, non-destructive, idempotent and closed-world, so the bar is lower. The description still earns credit by adding that the session table is local and in-memory and that the session is neither modified nor deleted, but it is silent on failure behavior such as unknown tokens or a missing/expired session.

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?

Two compact sentences with no filler; the core operation is front-loaded in the first clause and the non-mutation guarantee follows. Slightly redundant opening ("Drop-in ZTDS RFC v1.0 restoration tool" restates the title) keeps it from a 5.

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?

A low-complexity two-parameter read tool with no output schema and full annotations — the description covers what it does, the mechanism, and the non-destructive guarantee, which is sufficient to call it. Only edge-case behavior (missing session, unrecognized tokens) is unaddressed, a minor gap at this complexity.

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 both 'text' and 'sessionId' are already documented in the schema, including the default and its link to ztds_sanitize. The description adds no additional semantic detail about accepted token formats or session scoping beyond what the schema states.

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?

Names a specific verb ("Rehydrates") and resource ("surrogate tokens back into original cleartext") and pins down the mechanism (local in-memory session table). An agent can tell this is the inverse of sanitization, though it never names a sibling such as reveal_text or guard_rag_restore to disambiguate the restore family.

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?

Usage is implied rather than stated: the sessionId description ties it to the session passed to ztds_sanitize, which sketches the workflow. There is no explicit when-to-use/when-not-to-use guidance and no disambiguation from reveal_text, stream_reveal_text, or guard_rag_restore, which plausibly overlap.

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