mnemosyne_ask

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

With no annotations provided, the description carries the full burden of behavioral disclosure print and does it thoroughly. It reveals the RAG pipeline internals (deeper retrieval, lexical fusion, re-rank), the latency (~30s), and the fact that prose is a model rewording, not verbatim memory. It also warns to always check sources before trusting the answer. No contradiction with annotations exists because none are present.

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 description is dense and front-loaded: the first sentence states the core purpose; subsequent sentences add pipeline, latency, and trust caveats. There is slight redundancy in repeating the retriever claim ('better RETRIEVER' and 'reach for it whenever you need to find something'), but all sentences earn their place given the important caveats.

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?

Given there is no output schema and no annotations, the description is remarkably complete. It tells the agent what to expect (prose plus a Sources list), how long it might take, what question types work well, and how to responsibly use the output. Missing only trivial details, such as explicit error behavior, which are not necessary for correct invocation.

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 the baseline is 3. The schema already fully documents both parameters, including the scope_denied behavior for unrecognized vaults and the 'ask a knowledgeable colleague' guidance for the question. The description itself adds no parameter-specific detail beyond general context.

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 ('Ask'), a resource ('Mnemosyne'), and a concrete outcome ('a SYNTHESIZED prose answer grounded in the vault, PLUS the chronicles it drew on'). It also explicitly differentiates itself from sibling mnemosyne_query by claiming to be the better retriever and noting it is slower. There is no ambiguity about what the tool does.

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 description gives explicit when-to-use guidance: 'reach for it whenever you need to find something' and 'Best on "why / who / how" questions spanning many memories'. It also names mnemosyne_query as the faster alternative and instructs users to fetch sources with it when exact quotes are needed. It includes a clear when-not-to-trust warning: never quote the prose; check the sources first.

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