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

Annotations only declare readOnlyHint=true; the description adds substantial context beyond that: hybrid vector + keyword retrieval, reranking, a no-fabrication grounding guarantee, and the critical prerequisite that content must be plaintext-indexed server-side and is therefore outside the E2EE guarantee. That last point is exactly the kind of hidden constraint an agent cannot infer from the schema.

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 core purpose and use cases are front-loaded before the security caveat, and each clause carries information. The security note is long relative to the rest, but it is genuinely load-bearing rather than filler.

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 no output schema, the description still tells the agent what comes back ('an answer plus the source snippets it used'). Combined with the indexing prerequisite and the security caveat, an agent has everything needed to decide whether calling it is both correct and permissible.

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% and every parameter (query, top_k, thread_id, source_types) is already documented in-schema, including the 'file' and 'ptt' source-type quirks, so the baseline of 3 applies. The description adds only that sources are 'cited' and 'reranked', which does not meaningfully deepen parameter meaning.

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 (search and answer) and resource (the USER'S OWN mosadd data — messages, emails, calls, notes) with the retrieval mechanics spelled out. The parenthetical 'mRAG = RAG over your own data' plus the source-type enumeration clearly separates it from mRAG_ingest, mRAG_graph_neighbors, and mRAG_list_sources.

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 three concrete use cases ('what did X say about Y', summarize a thread, pull facts the user has received) and notes it works outside the mosadd app, which sets real invocation context. It stops short of explicit exclusions — it never says to use mRAG_graph_neighbors for relationship queries or mRAG_list_sources to enumerate what's indexed.

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