Skip to main content
Glama
Sign In
mcp-hyperspace-memory

mcp-hyperspace-memory

Official
by YARlabs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

memory_consolidate

Consolidate a cluster of related episodic memories into a single semantic concept using a hyperbolic Fréchet mean, optionally persisting the summary and archiving sources.

Instructions

Consolidate a cluster of related episodic memories into a single abstract semantic concept using the Fréchet Mean on the hyperboloid. Optionally stores the synthesized summary_text back into memory (persist: true) and cleans up source memories (archive_sources: true). Returns a JSON report with consolidated_id, mean vector, and source IDs.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "topic_query": "<topic_query>"
    },
    "name": "memory_consolidate"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNumber of memories to consolidate (default: 10).
persistNoWhether to store the consolidated concept into memory (default: true).
topic_queryYesA topic or query to identify the cluster of memories to consolidate.
summary_textNoOptional: synthesized summary or abstract statement representing the consolidated concept.
archive_sourcesNoWhether to delete/purge the source episodic memories after consolidation (default: false).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv4.2.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations at all, the description still discloses the two consequential behaviors: persist defaults to true and writes summary_text back, and archive_sources deletes/purges the source memories. It also states the return shape (consolidated_id, mean vector, source IDs). It stops short of saying whether purging is irreversible or what happens if too few memories match.

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

Conciseness4/5

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

Three sentences, front-loaded with the core action and then the optional side effects, with essentially no filler. The algorithmic jargon is informative rather than padding, though it could be trimmed for a purely operational reader.

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 five-parameter mutation tool with no annotations and no output schema, the description covers the action, the destructive option, the defaults, and the return fields. The remaining gap is the unstated interaction between the default persist=true and the optional summary_text, which leaves an agent unsure what is actually written.

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 coverage is 100%, so all five parameters are already documented, which sets the baseline at 3. The description adds only modest value beyond that by linking persist to summary_text storage and archive_sources to source cleanup, but it never resolves what gets persisted when persist is true and summary_text is omitted.

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 names a specific verb and resource (consolidate a cluster of episodic memories into a semantic concept) and even names the mechanism (Fréchet Mean on the hyperboloid). No sibling tool in the list performs consolidation, so an agent can route to it unambiguously.

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

Usage Guidelines3/5

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

Usage is only implied: the reader infers you call this when you want to abstract a group of related memories. The optional flags (persist, archive_sources) hint at scenarios but the description never states when to prefer this over memory_update, memory_link, or plain memory_remember, nor any precondition such as a minimum cluster size.

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