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

The annotations declare readOnlyHint=false, so mutation is already known; the description adds real value by disclosing what gets destroyed, specifically that per-user-indexed content and metadata are stored server-side in plaintext and are NOT covered by the E2EE/zero-knowledge guarantee. That disclosure is exactly the kind of behavior an agent needs before a write. It falls short of a 4-5 because it does not state whether re-ingesting the same document overwrites or duplicates, any size/rate limits, or error behavior.

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?

The primary action and the critical corpus caveat are front-loaded and the warning is scoped with ⚠ so it reads as a deliberate exception rather than noise. It is dense but slightly long, with the plaintext-privacy note and the graph warning stacked into one block.

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 14 parameters, one required, and no output schema, the description still covers the three things that matter: what the tool does with content, what it returns ('how many chunks were indexed'), and the privacy/storage caveat. An agent has everything needed to call it correctly, including how this call determines whether sibling graph tools return anything.

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%, so the baseline is 3; the description nonetheless adds meaning beyond the schema by explaining the cross-tool consequence of omitting sender/recipient/occurred_at (an empty graph however many documents were loaded) and the ref-reuse merging rule. That is behavioral impact the schema text implies only partially, lifting it above 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?

Opens with a specific verb+resource ('Add text to the USER'S OWN private knowledge base') and immediately names its downstream consumer, mRAG_search, which distinguishes it from every sibling. The pipeline description ('semantically chunked, embedded (1536-d) and stored in the per-user vector index') makes the mechanism unambiguous.

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?

Explicitly states when to use it (a note, document, transcript, pasted page) and adds a conditional branch for corpus ingestion with the exact fields required (sender / recipient / occurred_at). It also names the affected alternatives (mRAG_graph_overview / _neighbors / _timeline) and warns what happens if they are omitted — an unusually complete when/when-not/alternatives statement.

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