Redact PII and secrets from prompt text locally using zero-egress invariants before LLM transmission.
Sanitize sensitive PII and secrets in prompt text locally using ZTDS RFC v1.0 zero-egress invariants.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The raw text to sanitize before sending to LLM context. | |
| sessionId | No | Optional session identifier to preserve token consistency across conversational turns (default: "default"). |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, but it does disclose a meaningful trait: sanitization runs 'locally' with 'zero-egress invariants', meaning text never leaves the host. However, it omits whether the operation is reversible (implied by sibling ztds_restore), what happens to session state, or how detection boundaries are determined.
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 wasted clauses. The jargon ('ZTDS RFC v1.0 zero-egress invariants') is slightly opaque but does not impede scanning or intent.
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 mutation tool with no annotations and no output schema, the description covers the core action and the local/zero-egress trait but leaves the agent without reversibility expectations, return behavior, or the relationship to ztds_restore. Adequate but with clear gaps.
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 description coverage is 100%, so both parameters (text and sessionId) are already fully documented in the schema. The description adds no syntax, format, or default details beyond that, so the baseline 3 applies.
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?
The description gives a specific verb (Sanitize) and resource (sensitive PII and secrets in prompt text), which clearly distinguishes the action. It does not name sibling ztds_restore, which is the natural inverse, but the sanitize-vs-restore distinction is inferable from the verbs themselves.
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?
No explicit when-to-use, when-not, or alternative routing is provided. A sibling ztds_restore exists for reversing sanitization, but the description never mentions it or states the conditions under which this tool should be chosen over ztds_audit or ztds_info. Usage is only vaguely implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.