Skip to main content
Glama
Mnemosyne-OS

Mnemosyne OS

by Mnemosyne-OS
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

mnemosyne_memory_ask

Read-only

Ask a question and get a prose answer grounded in your memory vault, with sources. Uses local retrieval, lexical fusion, and re-ranking to find relevant memories. Best for why, who, how questions.

Instructions

Ask a question and get a prose answer grounded in the vault, plus the memories it drew on. It runs the full local RAG pipeline: deeper retrieval, lexical fusion and a re-rank. That also makes it the better retriever, so reach for it whenever you need to find something, and read the Sources list even if you ignore the prose. It is at its best on why, who and how questions that span many memories. It takes up to about 30 seconds. The prose is a model rewording of the sources, so quote the sources instead, or fetch them with mnemosyne_memory_query. Check them before you trust the answer.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vaultNoVault to reason over, case-insensitive. Default for this deployment: "DEV". A vault this server was not configured for is refused with SCOPE_DENIED.DEV
questionYesA question in plain language, the way you would ask a colleague who knows the material. Be specific.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.6.0-infinity
    • changedInput schema / properties / question / description
      Previous value: -"A natural-language question, as you would ask a knowledgeable colleague. Be specific."New value: +"A question in plain language, the way you would ask a colleague who knows the material. Be specific."
    • changedInput schema / properties / vault / description
      Previous value: -"Vault to reason over (case-insensitive). Default for this deployment: \"DEV\". A vault not declared to this MCP is refused with SCOPE_DENIED."New value: +"Vault to reason over, case-insensitive. Default for this deployment: \"DEV\". A vault this server was not configured for is refused with SCOPE_DENIED."
  2. Addedv1.5.1-infinity

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true, so safety is covered. The description goes beyond by disclosing performance (up to 30 seconds), the nature of the prose (a model rewording, so quote sources instead), and instructing to verify sources before trusting the answer. This adds rich, non-obvious behavioral context that helps the agent set expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact yet dense, with each sentence serving a distinct purpose: main action, pipeline details, usage guidance, performance caveat, and source-trust warning. It front-loads the core purpose and avoids fluff, making it efficient for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with no output schema, it fully describes the output (prose + sources), performance characteristics, and trust considerations. It also explains why to use the Sources list, covering all the information an agent needs to invoke and interpret the result correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for both parameters, so the schema already documents them. The description adds extra nuance on the question parameter ('plain language, the way you would ask a colleague who knows the material') and clarifies vault behavior, providing value beyond the schema without being redundant.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

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 (the vault), and the exact output (prose answer plus sources). It explicitly differentiates itself from siblings like mnemosyne_memory_query by positioning itself as the better retriever, leaving no ambiguity about what it does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance: 'reach for it whenever you need to find something' and identifies its sweet spot ('why, who and how questions that span many memories'). It also names the alternative (mnemosyne_memory_query) for fetching sources, so the agent knows exactly when to choose this over a sibling.

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

Deploy Server

Other Tools