Locally masks API keys, PII, and credentials in code, logs, or documents before sending to an LLM, preventing sensitive data exposure.
Zero-egress local DLP: Masks API keys, PII, and credentials in code, .env, or logs before feeding to LLM.
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | Raw code, log, or document text to redact |
Changes observed during successful MCP inspections.
v0.1.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. 'Zero-egress local DLP' is a genuinely useful disclosure (no network transmission, runs locally), but it does not say what the tool returns, how masks are represented, or whether masking is reversible/deterministic — significant gaps for a mutation-shaped tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no filler: the safety property ('Zero-egress local') and the action ('Masks ... before feeding to LLM') both land immediately. Nothing to trim.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter tool this is close, but with no annotations and no output schema the description should state what comes back (masked text, placeholders, mapping) so the agent knows the result is safe to forward. That return-behavior gap is the main missing piece.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a single well-described parameter ('Raw code, log, or document text to redact'). The description adds no parameter-level detail such as size limits, encoding expectations, or multi-document handling, so it does not exceed what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ('Masks') and concrete targets (API keys, PII, credentials) across named input types (code, .env, logs). It is clearly a redaction tool and does not overlap with the sibling tools (integrity verification, action inspection, credit upgrade), though it never explicitly contrasts itself with them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'...before feeding to LLM' implies the usage context, so an agent can infer this is a pre-flight sanitization step. However, there are no explicit when-to-use/when-not conditions, no mention of alternatives, and no statement about whether this replaces or complements truthgate_inspect_action or truthgate_verify_test_integrity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.