holonovel

Belief Management

manage_belief

Destructive

Record, inspect, and reconcile what each entity believes by admitting, retracting, or resolving evidence and contradictions, separate from objective truth, shared lore, or raw observation.

Instructions

Manage per-entity evidence and reconciled belief stances — one entity's subjective epistemic state, distinct from objective truth, shared lore, and raw observation. Mutating actions (admit, retract, reconcile) persist to the Novel and are audited; list/get/evidence/conflicts are read-only. Revert the most recent mutation with manage_history (action: undo). Use when: recording what an entity has learned or believes (admit), suppressing a piece of evidence (retract), inspecting current stances (list), reading one question (get), listing supporting evidence (evidence), finding unresolved contradictions (conflicts), or forcing recomputation (reconcile). Do NOT use when: recording objective world truth — use manage_causal or manage_world; recording shared lore — use manage_lore; recording raw observation — use manage_perception; recording consumed reference material — use manage_corpus.

Input Schema

TableJSON Schema

Name	Required	Description
`action`	Yes	list, get, evidence, admit, retract, conflicts, or reconcile.
`object`	No	Proposition object (admit).
`source`	No	Source key used to correlate duplicate evidence (admit; default the active badge).
`status`	No	active, unresolved, or suppressed (admit; default active).
`weight`	No	Evidence support weight 0..1 (admit; default 1).
`subject`	No	Proposition subject (admit).
`polarity`	No	positive or negative (admit).
`question`	No	Belief question key, or subject\|predicate\|object (get/evidence).
`entity_id`	No	Entity whose beliefs are queried or mutated.
`predicate`	No	Proposition predicate (admit).
`evidence_id`	No	Evidence record id (retract).
`source_ordinal`	No	Contributing event-log ordinal (admit; default the latest event ordinal).

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, but the description adds action-level transparency: mutating actions admit, retract, and reconcile persist to the Novel and are audited, while list/get/evidence/conflicts are read-only. It also notes that the most recent mutation can be reverted with manage_history. It stops short of detailing permissions or exact undo scope, but goes well beyond the 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?

The description is dense but well-structured: a definition, a mutating/read-only split, a revert note, and then explicitly labeled 'Use when' and 'Do NOT use when' sections. Every sentence serves routing or selection, and the most important distinctions are front-loaded.

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?

Given a 12-parameter tool with an output schema and rich annotations, the description covers purpose, action semantics, mutability, alternates, and a revert path. Output values are left to the output schema, and safety hints are covered by annotations. Nothing critical for correct invocation is missing.

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%, so the schema already documents all 12 parameters in detail. The description adds meaning for the action enum by mapping each action to an intent (e.g., admit for recording what an entity believes, retract for suppressing evidence), but does not elaborate on the other parameters beyond what the schema provides. Baseline 3 is appropriate.

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 states a specific verb and resource, defines the domain as per-entity subjective epistemic state, and explicitly distinguishes it from objective truth, shared lore, raw observation, and consumed reference material. It names the sibling tools for each contrasting domain, making it easy to route correctly.

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 provides explicit 'Use when' guidance mapping each action to a concrete scenario and a 'Do NOT use when' section that names alternatives (manage_causal, manage_world, manage_lore, manage_perception, manage_corpus). The inclusion of the revert path via manage_history further clarifies the lifecycle.

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