guard_rag_restore

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds meaningful context beyond them: the authentic values live only in volatile RAM session state, which tells an agent that restoration is session-bound and will not work after a reset. It stops short of saying what happens when the session is missing or expired.

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?

It is a single sentence with the operative verb ('Re-hydrates') placed early and the constraint ('before presenting to the user') at the end. The leading brand phrase 'Zero-Trust Agentic Guard:' adds no routing value and is the only real waste.

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?

With only two parameters, full schema coverage, and no output schema, the description covers the essential mechanic. It still leaves open the return shape (presumably the same results with placeholders substituted) and the failure mode when tokens have no matching session entry, both of which an agent would want before calling.

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%, including the accepted shapes for the results array and the session_id default, so the schema carries parameter documentation. The description's only added semantic is that restoration draws on session-scoped RAM data, reinforcing why session_id matters, but it adds no format or edge-case detail beyond that. Baseline 3 is appropriate.

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 states a specific verb and resource: re-hydrating retrieved vector search results/chunks by replacing token placeholders with original values from session memory. That is clearly distinguishable from siblings like sanitize_text or guard_rag_chunk (the redaction direction). It does not explicitly name the inverse tool it pairs with, which keeps it below a 5.

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?

The phrase 'before presenting to the user' implies the lifecycle position: call this after retrieval and prior to display. However, no explicit when-not conditions or named alternatives (e.g., guard_rag_chunk for the redaction side, reveal_text for direct unmasking) are given, so routing is inferred rather than stated.

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