guard_rag_chunk

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 bar is lower. The description reinforces that with 'keeps authentic data in local RAM with zero network leakage', but it never says whether sanitized chunks are returned as a new array, whether placeholders are reversible via guard_rag_restore, or whether any audit record is produced.

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?

Two front-loaded sentences with the pipeline use case stated first. The 'Zero-Trust Agentic Guard' branding and the local-RAM claim are slightly promotional but the latter does carry a real behavioral fact.

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?

There is no output schema, so the description should explain the shape of what comes back (sanitized chunks, placeholder mapping, any findings), and it does not. For a guard/sanitizer whose output an agent must act on, that is a meaningful gap given the otherwise complete parameter documentation.

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 chunks, sector, profile, and session_id are fully documented in the schema itself. The description adds no meaning about profile selection, sector aliasing, or how session_id affects multi-task isolation, so it sits at the baseline.

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 (sanitizes) and resource (an array of document chunks / knowledge base records), plus the destination context (embedding models, vector DBs). It implicitly distinguishes itself from the string-level sibling sanitize_text by scoping to arrays, but never names a sibling explicitly.

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?

Gives a clear trigger condition: call this before sending chunks to embedding models or a vector database. It does not state exclusions (e.g. use sanitize_text for a single string, or guard_rag_restore to rehydrate) so the agent must infer the boundary from sibling names alone.

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