Skip to main content
Glama

mcp_diet_redact_text

Read-onlyIdempotent

Redact leaked API keys, GitHub PATs, AWS keys, connection URL passwords, bearer tokens, and private keys from input text before sharing or logging it.

Instructions

Redact leaked API keys, GitHub PATs, AWS keys, connection URL passwords, bearer tokens, and private keys from text.

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": "mcp_diet_redact_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesInput text to sanitize against secret leakage.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the description is not obligated to restate that. It adds value by enumerating the secret families matched, but omits the most consequential behavior: whether matches are replaced with a placeholder or removed, and whether original secrets appear anywhere in the result.

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

Conciseness5/5

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

A single front-loaded sentence with the verb first and the pattern list doing real work; no filler, no hedging, nothing that could be cut without losing information.

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 one-parameter, closed-world, non-destructive text transform with no output schema, the definition should say what comes back (redacted text, findings, or both) since nothing else documents the return shape. It covers what is detected but not the output contract, leaving a meaningful hole for a simple tool.

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?

Only one parameter with 100% schema description coverage, so the schema already explains that 'text' is the input to sanitize. The description lists detectable secret types, which informs the parameter's meaning slightly, but adds no format, size, or encoding constraints beyond the schema.

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?

Specific verb 'Redact' plus a concrete resource enumeration (API keys, GitHub PATs, AWS keys, connection URL passwords, bearer tokens, private keys), so an agent knows exactly the class of operation and the detected pattern families. No sibling differentiation is offered, though the three siblings (analyze_tools, read_spill, status) are unrelated enough that confusion is unlikely.

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 only implied: an agent can infer it should call this when text may contain credentials, but there is no explicit when-to-use framing, no prerequisites, and no mention of what to do instead for non-secret sanitization or analysis. Adequate but with clear gaps in routing guidance.

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