holonovel

Relationship Management

manage_relationship

Destructive

Set or read directed relationships between entities, NPCs, or factions. Changes persist to the Novel; use manage_history to undo.

Instructions

Manage directed relationships between entities, NPCs, or factions. Mutating actions persist to the Novel and are audited; read-only actions do not mutate state. Revert the most recent mutation with manage_history (action: undo). Use when: setting or reading how two parties relate. Do NOT use when: tracking faction progress — use manage_faction (action: update).

Input Schema

TableJSON Schema

Name	Required	Description
`type`	No	Relationship type (set).
`value`	No	Optional relationship strength (set).
`action`	Yes	set or get.
`entity_a`	No	The source entity (set).
`entity_b`	No	The target entity (set).
`entity_id`	No	Entity whose relationships to list (get).
`description`	No	Optional description (set).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`text`	No	Human-readable text envelope mirroring the structured result (REQ-001, REQ-548a).
`status`	Yes	Machine-readable result status: OK, NEED_INPUT, WARNING, PARTIAL, or an error category (REQ-002, REQ-548c).

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.0.3Sep 29, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false; the description adds genuinely new context by explaining that mutating actions persist to the Novel and are audited, that read-only actions do not mutate state, and that the last mutation can be reverted through manage_history.

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?

Four sentences, none wasted: scope, persistence/audit behavior, revert route, and use/do-not-use routing are all front-loaded and each earns its place.

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 exists so return values need no explanation, annotations cover safety, and the description supplies the missing behavioral and routing context (persistence, audit, undo, sibling disambiguation) needed to call this correctly among 30+ siblings.

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% and two enums (action, type) are already documented in the schema, so the description adds little beyond restating that it sets or reads relationships. Baseline 3 is appropriate when the schema carries parameter meaning.

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 (manage) and resource (directed relationships between entities, NPCs, factions), plus names the sibling it must not be confused with (manage_faction). An agent can distinguish it from the 30+ other manage_* tools without opening the 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?

Explicit when-to-use ('setting or reading how two parties relate') and when-not ('tracking faction progress — use manage_faction (action: update)'), plus an alternate recovery path via manage_history (action: undo). This is the full when/when-not/alternative triad.

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