mnemosyne_memory_ask

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

With no annotations, the description carries the full burden, and it does so thoroughly. It discloses the RAG pipeline behavior, latency up to ~30s, the fact that output is a model reworded synthesis rather than verbatim memory, the presence of a Sources list, and a strong hallucination-safety warning. This is far beyond a simple 'ask a question' summary.

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 longer than average but information-dense and front-loaded with the core function, followed by usage guidance, latency, and safety warnings. Nearly every sentence earns its place; the dated benchmark 'measured on 2026-08-31' and the detailed pipeline parenthetical add credibility but are slightly expendable.

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?

For a tool with no annotations and no output schema, the description is surprisingly complete: it covers what the tool returns (synthesized prose plus sources), how long it takes, which sibling to compare against, how to phrase questions, and critical trust caveats. An agent has everything needed to invoke it correctly and interpret its output safely.

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, but the description adds meaningful invocation guidance beyond the schema: concrete example questions ('why was SQLite chosen over Postgres?', 'who is <name> and what do they own?') and the type of questions it is best for. It does not add detail about the vault parameter, but the schema already documents the default and scope-denial behavior.

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 opens with a specific verb+resource: 'Ask Mnemosyne a question and get a SYNTHESIZED prose answer grounded in the vault, PLUS the chronicles it drew on.' It clearly differentiates from the sibling mnemosyne_memory_query by explicitly positioning this tool as both the reasoning tool and the better retriever, and by naming the slower latency tradeoff.

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?

Usage guidance is explicit and actionable: 'reach for it whenever you need to find something', 'Best on "why / who / how" questions spanning many memories', and 'Slower than mnemosyne_memory_query (up to ~30s)'. It also tells the agent when to switch to the alternative ('fetch them with mnemosyne_memory_query'), covering both when-to-use and when-not-to-quote-prose.

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