Skip to main content
Glama

Player Character Management

manage_character
Destructive

Create, import, stage, activate, edit, signal, remove, or list player characters to keep a Novel's roster and active playable entity current.

Instructions

Manage player characters: create, import, stage, activate, edit, signal, remove, or list roster characters. stage adds an existing entity to the roster; set_active chooses which Novel entity play acts through and optionally sets pov; import requires roster_id and copies that roster character into the Novel. sheet and roster_list are read-only; Novel mutations persist, are audited, and are undoable via manage_history (action: undo). update merges provided fields (stats shallow-merge; omitted fields preserved), personality{} aliases description/voice/background/goals, and details{} aliases ability_scores/skills/feats/talents/equipment; a top-level value overrides its grouped alias. stage and roster_remove are exact inverses on the roster; remove deletes the Novel entity and is undoable. Use when: creating or importing a PC, staging or activating one for play, editing its sheet or voice, or handling player feedback. Do NOT use when: managing an NPC — use manage_npc.

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_character"
  }
}

Input Schema

NameRequiredDescriptionDefault
povNoPoint-of-view mode (set_active).
nameNoCharacter name; omit (create) to begin step-by-step.
seedNoDeterministic seed (create).
featsNoFeats (create).
goalsNoCharacter goals (create/personality).
statsNoMechanical stat keys to shallow-merge into the entity's stats (update).
valueNoFeedback text (signal).
voiceNoVoice and speech pattern (create/personality).
actionYescreate, stage, import, sheet, set_active, personality, voice, signal, update, remove, roster_remove, or roster_list.
formatNoOutput format (sheet).
signalNoFeedback category (signal).
skillsNoTrained skills (create).
classesNoClass levels (create).
detailsNoGrouped mechanical details (create).
speciesNoSpecies (create).
talentsNoTalents (create).
examplesNoVoice examples (voice).
entity_idNoEntity identifier (stage/sheet/set_active/personality/voice/remove).
equipmentNoStarting equipment (create).
inventoryNoReplace the entity's inventory (update).
roster_idNoRoster identifier (import/roster_remove).
backgroundNoBackstory (create/personality).
descriptionNoNarrative description (create/personality).
personalityNoGrouped personality fields (create).
stat_methodNoStat-generation method (create).
ability_scoresNoAbility scores (create).
stage_to_rosterNoAlso stage into the roster (create).

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. Changed4 schema fields changedv1.0.5
    • changedInput schema / properties / action / description
      Previous value: -"create, stage, import, sheet, set_active, personality, voice, signal, remove, roster_remove, or roster_list."New value: +"create, stage, import, sheet, set_active, personality, voice, signal, update, remove, roster_remove, or roster_list."
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "create",
      -  "stage",
      -  "import",
      -  "sheet",
      -  "set_active",
      -  "personality",
      -  "voice",
      -  "signal",
      -  "remove",
      -  "roster_remove",
      -  "roster_list"
      -]New value: +[
      +  "create",
      +  "stage",
      +  "import",
      +  "sheet",
      +  "set_active",
      +  "personality",
      +  "voice",
      +  "signal",
      +  "update",
      +  "remove",
      +  "roster_remove",
      +  "roster_list"
      +]
    • addedInput schema / properties / inventory
      Added value: +{
      +  "description": "Replace the entity's inventory (update).",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedInput schema / properties / stats
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "Mechanical stat keys to shallow-merge into the entity's stats (update).",
      +  "propertyNames": {
      +    "type": "string"
      +  },
      +  "type": "object"
      +}
  2. Addedv1.0.3

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the annotations: discloses which actions are read-only (sheet, roster_list), that Novel mutations persist and are audited, and that they are undoable via manage_history (action: undo), plus that remove deletes the Novel entity while roster_remove is its exact inverse of stage. This meaningfully softens/clarifies the destructiveHint=true profile. It stops short of stating auth/permission requirements or failure modes for the destructive path.

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-loads the action inventory and puts the use/don't-use routing at the end, which is a sensible structure. It is information-dense and nearly every clause earns its place, but the long semicolon-chained middle section (alias/override rules, inverse pairs) is harder to scan than it needs to be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-action, 27-parameter tool this covers the high-risk semantics well: mutation persistence, undo path, delete vs roster_remove, merge/override rules, and the NPC boundary. Return values need not be explained because an output schema exists. Minor gaps remain around the read-only actions' 'format' option and the meaning of individual signal categories.

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 real semantics the schema cannot express: update shallow-merges stats and preserves omitted fields, personality{} aliases description/voice/background/goals, details{} aliases ability_scores/skills/feats/talents/equipment, a top-level value overrides its grouped alias, and import requires roster_id. Many create-only parameters (species, classes, stat_method, seed, format, examples) are still only explained by the schema, so it is not exhaustive.

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?

Opens with a specific verb+resource ('Manage player characters') and enumerates the twelve supported actions, plus a one-line gloss for the ambiguous ones (stage, set_active, import). It explicitly distinguishes the tool from manage_npc, so an agent can route without opening either 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 explicit 'Use when' (creating/importing a PC, staging or activating for play, editing sheet or voice, handling player feedback) and 'Do NOT use when: managing an NPC - use manage_npc', naming the alternative tool directly. Nothing about selection is left to inference.

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