Skip to main content
Glama

Embers: Tabletop RPG Toolkit

Get a vault authoring guide

vault_get_authoring_guide
Read-onlyIdempotent

Fetch a markdown reference guide that teaches the conventions for authoring a specific entity type in a specific ruleset. Returns the full markdown body, including front-matter metadata (ruleset, entityType, version) at the top. Entity types: 'monster' — monster stat-block authoring (the field map, the stat block math, action types, spell formatting, resistances/immunities, keywords, a worked example), authored via vault_build_monster or vault_create_character + vault_update_character; 'rule' — classes / species / backgrounds / feats / abilities (the type taxonomy, the parent→Ability grant model, type-specific section fields, and the shared mechanics blocks: proficiencyChoices, spellChoices, spellListChoices, preparedSpells, freeCast, uses, ruleChoice, statBonuses), authored via vault_create_rule + vault_update_rule; 'spell' — the spell detail header (casting time / range / area / components / duration), the categories (Class(es)) membership convention, the damage/healing/effect mechanics blocks with upcasting (spellSlot scaling and slotIncrement), recurringDamage with its scaling and save, and extraDamage (a second damage packet), authored via vault_create_spell + vault_update_spell. Pass the ruleset code you are authoring for (list_rulesets gives the codes). Call this BEFORE authoring the matching entity so the result follows the established conventions instead of inferring shape from one-off samples. Returns a 'not found' tool error when the requested entityType / rulesetCode combination does not have a published guide yet.

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": {
      "entityType": "<entityType>"
    },
    "name": "vault_get_authoring_guide"
  }
}

Input Schema

NameRequiredDescriptionDefault
entityTypeYesEntity the guide covers: 'monster', 'rule' (classes / species / backgrounds / feats / abilities), or 'spell'. Lowercase. A ruleset / entity pair with no published guide returns not found.
rulesetCodeNoRuleset code, from list_rulesets. Use the code, not the display label.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / entityType / description
      Previous value: -"Entity the guide covers. Published for 5e24: 'monster', 'rule' (classes / species / backgrounds / feats / abilities), and 'spell'. Other entity types and rulesets land as separate guides over time. Lowercase."New value: +"Entity the guide covers: 'monster', 'rule' (classes / species / backgrounds / feats / abilities), or 'spell'. Lowercase. A ruleset / entity pair with no published guide returns not found."
    • changedInput schema / properties / rulesetCode / description
      Previous value: -"Ruleset data value (e.g. '5th Edition', '5e24', 'PFRPG', 'PFRPG2', 'PF Playtest', 'Savage Worlds', 'Savage Embers', 'Solarian Conflict', 'Embers RPG'). Use the data value, not the display label."New value: +"Ruleset code, from list_rulesets. Use the code, not the display label."
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds real behavioral context: the return payload includes front-matter metadata (ruleset, entityType, version) and a missing guide surfaces as a 'not found' tool error rather than an empty result. It stops short of describing size or formatting of the markdown body, but that is largely covered by the output schema.

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 correctly — the first sentence states what is fetched and returned before the long enumeration. The middle sentence is a dense semicolon-separated wall that partly duplicates the schema's entityType options, which costs it a point, but nothing is truly extraneous given the audience needs to know what each guide contains.

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?

With only two fully documented parameters, an output schema, and complete annotations, the description leaves no ambiguity: what it returns, when to call it, what to call it before, and how failure manifests. Nothing an agent needs in order to invoke it correctly 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 coverage is 100% and both parameters are documented there, including the entityType values and the ruleset-code convention. The description's entity-type walkthrough adds conceptual framing but largely restates what the schema's entityType description already says, so the baseline 3 applies.

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+resource ('Fetch a markdown reference guide that teaches the conventions for authoring a specific entity type in a specific ruleset') and enumerates exactly which entity types are covered. It is unmistakable against siblings like vault_get_rule or vault_get_spell, which retrieve data rather than authoring conventions.

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?

Explicitly says when to call it ('Call this BEFORE authoring the matching entity so the result follows the established conventions instead of inferring shape from one-off samples') and names the downstream authoring tools per entity type (vault_build_monster, vault_create_rule + vault_update_rule, vault_create_spell + vault_update_spell). It also points to list_rulesets for obtaining the ruleset code and warns about the not-found case.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources