Embers: Tabletop RPG Toolkit

Build a 5e24 player character

vault_build_pc

Assemble a complete, playable 5e24 player character in one call from a flat draft of choices. Vault validates every pick against the user's own + stock content and builds the full sheet — ability scores (with background bump), skills, saves, hit points, starting equipment + derived weapon actions, granted rules / feats / abilities, trackables, and a creation-recap note. Read vault_get_pc_creation_options first to get legal ids and pools. Required: name, classRuleId, abilityScoreMethod, abilityScoreAssignments, skillProficiencies, toolProficiencies, startingEquipmentLabel. Required when present: backgroundFeatRuleId (an open featOpen background's Origin feat — the build rejects the draft without it). Optional: speciesRuleId, backgroundRuleId, backgroundSkillProficiencies (when the background grants skills as a choice), the background bump (backgroundBumpMode + backgroundBumpAssignments), backgroundFeatRuleId (as a swap on a fixed-feat background), languages, languageChoicePicks (background/species language-choice grants), alignment, description/image/appearances/token, and the choice maps (proficiencyChoicePicks, abilityChoices, speciesAbilityChoices, backgroundFeatChoices, equipmentChoices, weaponAbilityChoices, abilityBumpPicks) plus the spell maps (spellChoicePicks, spellListChoicePicks, preparedSpellPicks, castingAbilityPicks) for spellcasters / Magic-Initiate-style grants. proficiencyChoicePicks and spellChoicePicks are keyed ":" and only needed where a grant's count is smaller than its option pool. castingAbilityPicks is required for any spellChoices block surfacing castingAbilityOptions — the projection only surfaces that array when a pick is genuinely needed (a spellListChoices block's ability pick rides its spellListChoicePicks entry as castingAbility instead). The projected spellChoices/spellListChoices arrays may hold null entries (blocks inert at level 1) — count them when keying picks by index. A feat chosen via an ability's ruleChoice (in abilityChoices/speciesAbilityChoices) brings its own sub-choices — supply them in those same maps keyed by the picked feat's _id. A repeatable feat filling the background slot (backgroundFeatRuleId) instead prefixes its pick keys bg:<featId>. The created character is owned by the calling user and returned in full. On an invalid draft vault returns the specific reason (e.g. a pick out of pool, a wrong pick count, a missing required choice) as a tool error — fix the draft and retry.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 21, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Behavior is disclosed richly beyond the sparse annotations: the tool validates every pick, builds the full sheet, rejects drafts missing required feats, returns the created character in full, and returns specific error reasons on invalid drafts. Ownership is also stated: "The created character is owned by the calling user and returned in full." This is a high level of behavioral transparency for a creation action.

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?

The description is front-loaded with the core purpose and is information-dense with no filler; every sentence contributes. However, it is a single lengthy paragraph with heavy parentheticals, and it would be easier for an agent to parse with bullets or clearer section breaks. It is appropriately sized for the tool's complexity but not optimally structured.

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 the empty schema and minimal annotations, the description is remarkably complete. It covers the required prerequisite call, parameter categories, conditional requirements, key-encoding conventions, special background-feat cases, spellcaster handling, error behavior, and return value. An agent has enough context to attempt a correct call and to diagnose failures.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

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

The input schema is empty, so the description carries the full parameter burden, and it does so excellently. It enumerates required fields, conditionally required fields, optional fields, choice-map key formats like "<ruleId>:<grantIndex>", null-entry handling, and prefix rules such as "bg:<featId>". This goes far beyond the baseline 4 expected when there are zero schema-defined parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: "Assemble a complete, playable 5e24 player character in one call from a flat draft of choices." This gives a specific verb, resource, and scope. However, it does not explicitly differentiate itself from the similarly named sibling vault_create_character, instead relying on the phrase "complete... in one call" to imply the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: "Read vault_get_pc_creation_options first to get legal ids and pools," and it distinguishes required, conditionally required, and optional inputs. It does not, however, state explicit when-not-to-use cases or name alternative tools for simpler character creation flows, so it falls short of the full 5.

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

All Embers: Tabletop RPG Toolkit tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?