argo-mcp

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 16 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_GIVER (Quest → the NPC who gives it), QUEST_LOCATION (Quest → the Location where it is given or set), QUEST_RELATED_NPC (Quest → NPC), QUEST_RELATED_LOCATION (Quest → Location), SESSION_ATTENDEE_CHARACTER (SessionSummary → a character's 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 on the faction or affiliationEntryIds on the NPC; for a quest's giver, location and parent prefer giverId / locationId / parentQuestId on the quest, which keep each to one link. Session-summary links have no array equivalent — the SESSION_* labels are the only way to set them.

Input Schema

Name	Required	Description
`color`	No
`label`	Yes
`direction`	No	Deprecated: 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.
`campaignId`	Yes
`sourceEntryId`	Yes
`targetEntryId`	Yes

Output Schema

Name	Required	Description	Default
`kind`	No
`color`	No
`label`	Yes
`sourceId`	Yes
`symmetry`	No
`targetId`	Yes
`direction`	No
`relationshipId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 29, 2026

changedInput schema / properties / label / enum

Previous value: -[
-  "MEMBER",
-  "ALLY",
-  "ENEMY",
-  "RIVAL",
-  "PARENT_OF",
-  "CONTAINS",
-  "LOCATED_IN",
-  "HAS_SUBQUEST",
-  "QUEST_RELATED_NPC",
-  "QUEST_RELATED_LOCATION",
-  "SESSION_ATTENDEE_CHARACTER",
-  "SESSION_ATTENDEE_NPC",
-  "SESSION_FEATURED_QUEST",
-  "SESSION_FEATURED_LOCATION"
-]New value: +[
+  "MEMBER",
+  "ALLY",
+  "ENEMY",
+  "RIVAL",
+  "PARENT_OF",
+  "CONTAINS",
+  "LOCATED_IN",
+  "HAS_SUBQUEST",
+  "QUEST_GIVER",
+  "QUEST_LOCATION",
+  "QUEST_RELATED_NPC",
+  "QUEST_RELATED_LOCATION",
+  "SESSION_ATTENDEE_CHARACTER",
+  "SESSION_ATTENDEE_NPC",
+  "SESSION_FEATURED_QUEST",
+  "SESSION_FEATURED_LOCATION"
+]

Changed3 schema fields changedAug 6, 2026

addedInput schema / properties / direction / description

Added value: +"Deprecated: 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."

addedOutput schema / properties / kind
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / symmetry
```
Added value: +{
+  "type": "string"
+}
```

Changed1 schema field changedJul 21, 2026

changedInput schema / properties / label / enum

Previous value: -[
-  "MEMBER",
-  "ALLY",
-  "ENEMY",
-  "RIVAL",
-  "PARENT_OF",
-  "CONTAINS",
-  "LOCATED_IN",
-  "HAS_SUBQUEST",
-  "QUEST_RELATED_NPC",
-  "QUEST_RELATED_LOCATION"
-]New value: +[
+  "MEMBER",
+  "ALLY",
+  "ENEMY",
+  "RIVAL",
+  "PARENT_OF",
+  "CONTAINS",
+  "LOCATED_IN",
+  "HAS_SUBQUEST",
+  "QUEST_RELATED_NPC",
+  "QUEST_RELATED_LOCATION",
+  "SESSION_ATTENDEE_CHARACTER",
+  "SESSION_ATTENDEE_NPC",
+  "SESSION_FEATURED_QUEST",
+  "SESSION_FEATURED_LOCATION"
+]

Changed1 schema field changedMay 16, 2026

changedInput schema / properties / label / enum

Previous value: -[
-  "MEMBER",
-  "ALLY",
-  "ENEMY",
-  "RIVAL",
-  "PARENT_OF",
-  "CONTAINS",
-  "LOCATED_IN"
-]New value: +[
+  "MEMBER",
+  "ALLY",
+  "ENEMY",
+  "RIVAL",
+  "PARENT_OF",
+  "CONTAINS",
+  "LOCATED_IN",
+  "HAS_SUBQUEST",
+  "QUEST_RELATED_NPC",
+  "QUEST_RELATED_LOCATION"
+]

First observedMay 14, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations declare the safety profile (readOnly=false, destructive=false), and the description adds rich behavioral context beyond them: the label solely determines kind and direction, per-edge overrides must never be sent, and the server refuses contradictions. This is exactly the extra context the structured fields cannot carry.

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 governing rule ('The label decides everything') is front-loaded, and the dense 16-label enumeration each earns its place by encoding source/target type and read direction. It is long for a single tool but almost none of it is redundant 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?

Output schema handles return values, and the description covers what remains: the deprecated direction param, per-edge vs. array trade-offs, and the routing to describe_mnemon_types for the validation matrix. Nothing an agent needs to call it correctly is missing.

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

Parameters5/5

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

With only 17% schema description coverage, the description fully compensates: it defines sourceEntryId as the 'from' side and targetEntryId as the 'to' side with directionality warnings, explains each of the 16 label enum values with source→target semantics, and clarifies that 'direction' is deprecated.

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 first sentence states a specific verb+resource ('Create a relationship between two mnemon entries') and the rest scopes it precisely. An agent can distinguish it from delete_mnemon_relationship and list_mnemon_relationships at a glance.

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 explicitly routes the agent to alternatives: prefer memberNpcEntryIds/affiliationEntryIds for faction membership and giverId/locationId/parentQuestId on the quest for those links, and names SESSION_* labels as the only option for session links. It also points to describe_mnemon_types for the full matrix.

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

All argo-mcp tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Create mnemon relationship

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources