Skip to main content
Glama

Explore the knowledge graph around a memory

memory_graph
Read-onlyIdempotent

BFS walk from a memory node to map related concepts, supersession chains, or decision clusters. Returns neighbor nodes with typed edges. Read-only; use after searching memories to explore connections.

Instructions

BFS walk from one memory id outward, returning neighbour nodes + typed edges. Read-only. Use after memory_search to map related concepts, supersession chains, or the cluster around a decision. direction controls edge polarity (out/in/both); depth is capped at 5.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesMemory id to use as the root of the BFS walk.
depthNoHow many hops to traverse from the root (0-5). Default 2.
edge_typesNoOptional whitelist of edge types to follow. Omit to follow all types.
directionNo`out` follows outgoing edges only, `in` incoming only, `both` (default) follows all.both

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
foundYes`true` when the root memory exists. `false` when the id was not found (in which case `root` and `edges` are absent/empty).
rootNoRoot node metadata; absent when `found=false`.
edgesYesEdges discovered by the BFS walk, sorted by edge_type then by neighbour id.
Behavior4/5

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

Annotations already provide readOnlyHint=true and destructiveHint=false. Description adds behavioral details about BFS traversal (direction, depth cap of 5) and return type (neighbor nodes + typed edges), complementing annotations.

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?

Two concise sentences: first states action and result, second adds usage context and parameter hints. No redundancy or filler.

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?

Covers operation, usage context, and parameter constraints. With an output schema present, return values do not need elaboration. Complete for a graph exploration tool.

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 baseline is 3. Description briefly summarizes parameter roles (direction polarity, depth cap) but adds little beyond what schema descriptions already provide.

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 clearly states the verb (BFS walk) and resource (memory id outward), and distinguishes it from sibling tools like memory_search by specifying its role in exploring related concepts.

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

Usage Guidelines4/5

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

Explicitly recommends use after `memory_search` for mapping related concepts, supersession chains, or clusters. Lacks explicit when-not-to-use but provides clear context for appropriate use.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/lfrmonteiro99/memento-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server