Skip to main content
Glama
udjin-labs

mnemostack

by udjin-labs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Mnemostack Answer

mnemostack_answer

Answers natural-language questions by retrieving relevant stored memories and synthesizing a concise factual reply with citations and confidence, replacing raw search-result lists.

Instructions

Answer a question using retrieved memories.

Read-only, no side effects, no authentication required. Use this when you want a concise factual answer synthesized from memory search results instead of the raw matches returned by mnemostack_search. Returns a JSON object with ok, query, answer text, confidence (0.0-1.0), sources, notes (the AUTHORITATIVE routine signals — e.g. temporal:no_parse on any query without a date; NOT a fault), degraded (components that actually fell back, plus a deprecated back-compat duplicate of the routine tags until the next major), fallback_recommended, tokens_estimate (estimated text tokens of the context memories), tokens_used (LLM-provider-reported usage for the answer call; null when unreported), and error. Stale facts are hidden by default; use include_invalidated or as_of to see them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
as_ofNoPoint-in-time recall (ISO-8601); same contract as mnemostack_search.
limitNoMaximum number of results to return (default 10)
queryYesNatural language question or keyword to search memories for
filtersNoPayload filters applied inside every retriever (exact match or gte/lte ranges); the answer is generated only from memories inside the filtered scope.
token_budgetNoHard cap on the total (estimated) text tokens of the memories fed to the answer LLM (same contract as mnemostack_search). Unset uses the server-wide default.
include_invalidatedNoInclude facts marked stale (default false; same as mnemostack_search).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.8.0
    • addedInput schema / properties / as_of
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Point-in-time recall (ISO-8601); same contract as mnemostack_search."
+}
    • addedInput schema / properties / include_invalidated
      Added value: +{
+  "default": false,
+  "description": "Include facts marked stale (default false; same as mnemostack_search).",
+  "type": "boolean"
+}
    • addedInput schema / properties / token_budget
      Added value: +{
+  "anyOf": [
+    {
+      "minimum": 1,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Hard cap on the total (estimated) text tokens of the memories fed to the answer LLM (same contract as mnemostack_search). Unset uses the server-wide default."
+}
  2. Changed1 schema field changedv0.6.0
    • addedInput schema / properties / filters
      Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Payload filters applied inside every retriever (exact match or gte/lte ranges); the answer is generated only from memories inside the filtered scope."
+}
  3. Changed2 schema fields changedv0.4.3
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of results to return (default 10)"
    • addedInput schema / properties / query / description
      Added value: +"Natural language question or keyword to search memories for"
  4. First observedv0.4.1

TDQS

A4.4/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full disclosure burden and does so: read-only, no side effects, no authentication required, stale facts hidden by default, plus the important quirk that 'notes' are authoritative routine signals (e.g. temporal:no_parse) and NOT a fault, while 'degraded' means real fallback. This prevents an agent from misreading benign signals as errors.

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

Conciseness3/5

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

Purpose and usage are front-loaded, but a large block enumerates return fields (ok, query, answer, confidence, sources, error) that an output schema already provides, which is redundant length. The parenthetical clarifications of 'notes' and 'degraded' earn their place; the field listing largely does not.

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

Completeness4/5

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

For a six-parameter read tool with a full output schema, the description covers the safety profile, the usage decision, and the semantically ambiguous return fields (notes/degraded/fallback_recommended). It omits nothing an agent needs to call it correctly, though it could tie the token_budget/token_estimate relationship together more tightly.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all six parameters, establishing the baseline of 3. The description adds only marginal meaning beyond that ('Stale facts are hidden by default; use include_invalidated or as_of to see them'), restating contracts already present in the schema.

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?

States a specific verb+resource ('Answer a question using retrieved memories') and immediately differentiates itself from the sibling mnemostack_search by contrasting a synthesized answer with raw matches. An agent can pick this tool without opening either schema.

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?

Explicitly names the alternative ('instead of the raw matches returned by mnemostack_search') and the condition that selects it ('when you want a concise factual answer synthesized from memory search results'). It also flags the stale-data default and the include_invalidated/as_of escape hatch.

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