mnemosyne_query

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

There are no annotations, so the description carries the full behavioral burden — and it does so thoroughly. It discloses the ranking mechanism (vector similarity fused with BM25, weighted by spineType), warns that scores are not confidence indicators ('a miss and a hit come back with indistinguishable scores'), and discloses a concrete retrieval weakness on rare literal terms with a measurement date. This is far beyond the bare minimum with zero annotations 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 long but every sentence earns its place: purpose, rank-and-cite framing, sibling routing, and a critical score-confidence warning are all substantive. It is front-loaded with the primary purpose and uses ⚠️/⛔ markers to signpost warnings. Minor redundancy (the 'find something' phrasing repeats the ask-routing point) keeps it just short of perfect.

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 or annotations, the description covers the essential context an agent needs: what comes back, how results are ranked, how to interpret scores, and which sibling to choose instead. It does not describe the exact return fields of a result object, which would be a nice addition given the absent output schema, but the tool is otherwise complete enough to invoke correctly.

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 of 3 applies; the schema itself documents all five parameters (query examples, limit caps, vault token normalization, content-size limits, spine-type filtering). The description adds only modest parametric context — e.g., that ranking is weighted by spineType — but does not materially deepen per-parameter meaning beyond the schema.

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 opening line states a specific verb and resource ('Raw chronicle search in a Mnemosyne OS vault') and enumerates exactly what is returned (architecture notes, code, decisions, sessions, git history). It also distinguishes itself from siblings by emphasizing that nothing is rewritten and the source text comes back verbatim.

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?

It gives an explicit when-to-use ('this is what to use when you need the source text verbatim, e.g. to quote it or to write documentation from it') and a named alternative with a rejection condition ('prefer mnemosyne_ask even when you only want its sources', with a measured date explaining why). This is textbook when/when-not/alternatives guidance with no ambiguity.

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