Skip to main content
Glama

Belief Management

manage_belief
Destructive

Record, retract, reconcile, and query per-entity evidence, belief stances, and an append-only perception ledger; use it to inspect or update what a character learned or believes.

Instructions

Manage per-entity evidence, reconciled belief stances, the perception ledger, and a one-entity knowledge query. list, get, evidence, conflicts, perception_list, and knowledge_query read; admit, retract, reconcile, and perception_record write. admit records a subject/predicate/object proposition with a 0..1 weight and does not change a stance until reconcile recomputes it; retract requires the evidence_id from admit and reconciles; the perception ledger is append-only, so correct a mistaken perception with a new record. Mutating actions persist to the Novel. knowledge_query returns perceptions, beliefs, and known secrets with event provenance, optionally filtered by topic. Use when: inspecting or recording what an entity learned or believes. Do NOT use when: recording objective truth — use manage_causality; recording shared lore — use manage_lore; ranking derived text or traversing the knowledge graph — use manage_knowledge.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "manage_belief"
  }
}

Input Schema

NameRequiredDescriptionDefault
topicNoOptional topic filter applied to knowledge_query perceptions, beliefs, and secrets.
actionYesBelief: list, get, evidence, admit, retract, conflicts, or reconcile. Perception ledger: perception_record, perception_list, perception_for_entity, or perception_for_event. Knowledge: knowledge_query.
detailNoReturn full belief records instead of summary entries (list).
objectNoProposition object (admit).
sourceNoSource key used to correlate duplicate evidence (admit; default the active badge).
statusNoactive, unresolved, or suppressed (admit; default active).
weightNoEvidence support weight 0..1 (admit; default 1).
subjectNoProposition subject (admit).
polarityNopositive or negative (admit).
questionNoBelief question key, or subject|predicate|object (get/evidence).
entity_idNoEntity whose beliefs are queried or mutated.
predicateNoProposition predicate (admit).
evidence_idNoEvidence record id (retract).
source_ordinalNoContributing event-log ordinal (admit; default the latest event ordinal).
perception_kindNomessage, scene, or observation (perception_record; default observation).
perception_senseNoSense that produced the perception (perception_record; default null; REQ-594).
perception_room_idNoRoom identifier for the perception (perception_record; defaults to the entity's room).
perception_summaryNoWhat was perceived (perception_record).
perception_witnessNoWitness kind (perception_record; default inferred; REQ-594).
perception_entity_idNoEntity that perceived (perception_record/perception_for_entity).
perception_confidenceNo0..1 confidence (perception_record; default 0; REQ-594).
perception_event_ordinalNoContributing event-log ordinal (perception_record/perception_for_event; defaults to the latest event).
perception_source_entityNoEntity the perception came from (perception_record; default null).

Output Schema

NameRequiredDescriptionDefault
textNoHuman-readable text envelope mirroring the structured result (REQ-001, REQ-548a).
statusYesMachine-readable result status: OK, NEED_INPUT, WARNING, PARTIAL, or an error category (REQ-002, REQ-548c).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv2026.10.13
    • changedInput schema / properties / action / description
      Previous value: -"Belief: list, get, evidence, admit, retract, conflicts, or reconcile. Perception ledger: perception_record, perception_list, perception_for_entity, or perception_for_event."New value: +"Belief: list, get, evidence, admit, retract, conflicts, or reconcile. Perception ledger: perception_record, perception_list, perception_for_entity, or perception_for_event. Knowledge: knowledge_query."
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "list",
      -  "get",
      -  "evidence",
      -  "admit",
      -  "retract",
      -  "conflicts",
      -  "reconcile",
      -  "perception_record",
      -  "perception_list",
      -  "perception_for_entity",
      -  "perception_for_event"
      -]New value: +[
      +  "list",
      +  "get",
      +  "evidence",
      +  "admit",
      +  "retract",
      +  "conflicts",
      +  "reconcile",
      +  "knowledge_query",
      +  "perception_record",
      +  "perception_list",
      +  "perception_for_entity",
      +  "perception_for_event"
      +]
    • addedInput schema / properties / detail
      Added value: +{
      +  "description": "Return full belief records instead of summary entries (list).",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / perception_confidence
      Added value: +{
      +  "description": "0..1 confidence (perception_record; default 0; REQ-594).",
      +  "maximum": 1,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / perception_room_id
      Added value: +{
      +  "description": "Room identifier for the perception (perception_record; defaults to the entity's room).",
      +  "type": "string"
      +}
    • addedInput schema / properties / perception_sense
      Added value: +{
      +  "description": "Sense that produced the perception (perception_record; default null; REQ-594).",
      +  "enum": [
      +    "sight",
      +    "sound",
      +    "telling"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / perception_source_entity
      Added value: +{
      +  "description": "Entity the perception came from (perception_record; default null).",
      +  "type": "string"
      +}
    • addedInput schema / properties / perception_witness
      Added value: +{
      +  "description": "Witness kind (perception_record; default inferred; REQ-594).",
      +  "enum": [
      +    "saw",
      +    "heard",
      +    "inferred",
      +    "told"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / topic
      Added value: +{
      +  "description": "Optional topic filter applied to knowledge_query perceptions, beliefs, and secrets.",
      +  "type": "string"
      +}
  2. Changed6 schema fields changedv1.0.5
    • changedInput schema / properties / action / description
      Previous value: -"list, get, evidence, admit, retract, conflicts, or reconcile."New value: +"Belief: list, get, evidence, admit, retract, conflicts, or reconcile. Perception ledger: perception_record, perception_list, perception_for_entity, or perception_for_event."
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "list",
      -  "get",
      -  "evidence",
      -  "admit",
      -  "retract",
      -  "conflicts",
      -  "reconcile"
      -]New value: +[
      +  "list",
      +  "get",
      +  "evidence",
      +  "admit",
      +  "retract",
      +  "conflicts",
      +  "reconcile",
      +  "perception_record",
      +  "perception_list",
      +  "perception_for_entity",
      +  "perception_for_event"
      +]
    • addedInput schema / properties / perception_entity_id
      Added value: +{
      +  "description": "Entity that perceived (perception_record/perception_for_entity).",
      +  "type": "string"
      +}
    • addedInput schema / properties / perception_event_ordinal
      Added value: +{
      +  "description": "Contributing event-log ordinal (perception_record/perception_for_event; defaults to the latest event).",
      +  "type": "number"
      +}
    • addedInput schema / properties / perception_kind
      Added value: +{
      +  "description": "message, scene, or observation (perception_record; default observation).",
      +  "enum": [
      +    "message",
      +    "scene",
      +    "observation"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / perception_summary
      Added value: +{
      +  "description": "What was perceived (perception_record).",
      +  "type": "string"
      +}
  3. Addedv1.0.3

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations (destructiveHint=true, idempotentHint=false) by disclosing that admit does not move a stance until reconcile runs, that retract needs the evidence_id from admit and triggers a reconcile, that the perception ledger is append-only requiring a corrective record, and that mutations persist to the Novel. These are exactly the non-obvious state-machine facts an agent needs.

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?

Front-loaded and dense with real information, with the read/write split before the semantics and the use-when block at the end. The action enumeration slightly restates the action enum's own description, which is the only padding across 12 distinct operations.

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 23-parameter, 12-action tool with an output schema, the description covers action grouping, mutation lifecycle, persistence target, and return content for knowledge_query. The remaining detail lives in the 100%-covered schema and the output schema, so 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.

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds cross-action constraint meaning: evidence_id is only valid if obtained from admit, topic filters knowledge_query across perceptions/beliefs/secrets, and weight drives reconciliation rather than the stance directly. It does not, however, explain how the many perception_* fields relate to one another.

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?

Names the specific resource set (per-entity evidence, reconciled belief stances, perception ledger, knowledge query) and enumerates which actions read versus write. It also explicitly distinguishes itself from manage_causality, manage_lore, and manage_knowledge, so an agent can route correctly without opening any 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?

Provides an explicit 'Use when: inspecting or recording what an entity learned or believes' plus a 'Do NOT use when' block that names three sibling alternatives with the condition that selects each. This is the strongest form of routing guidance.

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