Skip to main content
Glama

argo-mcp

by io.github.Argo-RPG-Platform

Create mnemon relationship

create_mnemon_relationship

Create a relationship between two mnemon entries. The label decides everything: its kind (containment or association) and how it reads (one_way or mutual) belong to the word itself — never send a per-edge override. All 14 labels: MEMBER (NPC ∈ Faction, mutual), ALLY (mutual), ENEMY (one-way), RIVAL (one-way), PARENT_OF (Location hierarchy — sourceEntryId is the outer/larger place, e.g. Region → City → District → Tavern), CONTAINS (Location → NPC present there), LOCATED_IN (NPC → Location; inverse of CONTAINS), HAS_SUBQUEST (Quest → subquest Quest), QUEST_RELATED_NPC (Quest → NPC), QUEST_RELATED_LOCATION (Quest → Location), SESSION_ATTENDEE_CHARACTER (SessionSummary → CHARACTER-kind Player), SESSION_ATTENDEE_NPC (SessionSummary → NPC), SESSION_FEATURED_QUEST (SessionSummary → Quest), SESSION_FEATURED_LOCATION (SessionSummary → Location). sourceEntryId is the 'from' side; targetEntryId is the 'to' side — which end is which matters. Call describe_mnemon_types for the full valid (sourceType, label, targetType) matrix. For faction membership prefer memberNpcEntryIds / affiliationEntryIds on the NPC itself; for quest links prefer subQuestEntryIds / relatedNpcEntryIds / relatedLocationEntryIds on the quest. Session-summary links have no array equivalent — the SESSION_* labels are the only way to set them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
colorNo
labelYes
directionNoDeprecated: leave unset. The label alone decides the edge's shape — its kind and how it reads belong to the word (Mnemon D29/D33), and the server refuses a contradiction.
campaignIdYes
sourceEntryIdYes
targetEntryIdYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNo
colorNo
labelYes
sourceIdYes
symmetryNo
targetIdYes
directionNo
relationshipIdYes

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only indicate it's not read-only/destructive, so the description carries the burden. It discloses key behavioral traits: the label alone decides kind and reading (never send per-edge override), the server refuses contradictions, direction is deprecated, and the source/target sides are meaningful. It does not describe error handling or return format, but an output schema exists, so this is adequate.

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?

The description is long but every sentence is information-dense. It front-loads the core purpose, systematically lists all labels, explains directional rules, and closes with alternatives. While lengthy, the complexity of 14 labels and multiple edge types justifies the detail; no redundant or filler sentences.

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 low schema coverage, this description is remarkably complete. It covers the label matrix, direction semantics, when to prefer alternatives, and points to describe_mnemon_types for the full source/target matrix. The only unaddressed aspect is the optional color parameter, which is minor given the output schema exists and optional parameters are self-explanatory.

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 only 17% (only direction has a description), so the description must compensate. It thoroughly explains the label enum with all 14 values and their directional semantics, and clarifies sourceEntryId/targetEntryId as 'from'/'to'. However, the optional 'color' parameter is not mentioned in either schema or description, leaving a minor gap.

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 opens with a clear specific verb+resource: 'Create a relationship between two mnemon entries.' It immediately distinguishes from siblings like delete_mnemon_relationship and list_mnemon_relationships, and the detailed label semantics further clarify the tool's unique role in creating edges with label-defined behavior.

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?

The description explicitly states when to avoid this tool: for faction membership prefer memberNpcEntryIds/affiliationEntryIds on the NPC, and for quest links prefer subQuestEntryIds/relatedNpcEntryIds/relatedLocationEntryIds on the quest. It also notes that session-summary links have no array equivalent, making this the only way. Additionally, it directs to describe_mnemon_types for the full valid matrix, providing clear alternative guidance.

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

All argo-mcp toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose. The mnemon tools are separated by type (NPC, Location, Quest, etc.), and other domains like guild, forum, and friend management are also well-segmented. No two tools appear to do the same thing.

Naming Consistency4/5

Most tools follow a consistent verb_noun pattern with snake_case. Some minor deviations: 'describe_mnemon_types' instead of 'list_mnemon_types', and 'invite_user_by_email' has a slightly different structure. Overall quite consistent.

Tool Count3/5

With 63 tools, the server is quite heavy. While each tool serves a specific purpose for campaign management, the sheer number may be overwhelming. It is borderline but still reasonable given the broad domain coverage.

Completeness4/5

The tool set covers CRUD for most resources (campaigns, sessions, mnemon types, guilds, friends, forum). Notable gaps: no delete_campaign or delete_session, and update_campaign is limited. However, the core workflows are well-covered.

Resources