Skip to main content
Glama

Embers: Tabletop RPG Toolkit

Search vault items

vault_search_items
Read-onlyIdempotent

Search the item library the user has access to (stock items plus their own house items). Use this to locate an item by name, type (the catalog's own item types), or ruleset. Defaults to a compact summary shape (identification + summary + weight + cost + publisher / source); pass detail: 'full' to receive each item's full description and properties array inline.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "vault_search_items"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoMatches the item's name or any other name it is known by (a stock item with a generic name also answers to its rulebook name), ignoring case, apostrophe style, spaces, and hyphens. Results show the stock name. Use `^name$` for an exact match.
skipNoPagination offset; pair with `limit` to walk results.
sortNoComma-separated field list. Prefix with `-` for descending (e.g. `-updatedAt,name`).
typeNoItem type (substring, case-insensitive). Vault item types are ruleset-specific strings; an unfiltered search shows the types a ruleset's catalog uses.
limitNoPage size; defaults to 50 when omitted. Hard cap of 200.
stockNotrue = official content only; false = user-authored only; omit to include both.
detailNoResponse shape. 'summary' (default) returns identification + summary fields; 'full' returns the complete document shape (every field inline) that non-MCP clients receive by default.summary
rulesetNoRuleset code, from list_rulesets.
characterNoMongo `_id` of the vault Character you are picking content for (adding to its sheet, building or levelling it). Pass it whenever the results are offered for a particular Character: the stock records its Worlds hide are left out, as in the app's own pickers. An id that names no Character the user can see is ignored.

Output Schema

NameRequiredDescriptionDefault
resultsNo
paginationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / character
      Added value: +{
      +  "description": "Mongo `_id` of the vault Character you are picking content for (adding to its sheet, building or levelling it). Pass it whenever the results are offered for a particular Character: the stock records its Worlds hide are left out, as in the app's own pickers. An id that names no Character the user can see is ignored.",
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / name / description
      Previous value: -"Substring match on item name (case-insensitive). Use `^name$` for an exact match."New value: +"Matches the item's name or any other name it is known by (a stock item with a generic name also answers to its rulebook name), ignoring case, apostrophe style, spaces, and hyphens. Results show the stock name. Use `^name$` for an exact match."
  3. Changed2 schema fields changed
    • changedInput schema / properties / ruleset / description
      Previous value: -"Ruleset code (e.g. '5th Edition', '5e24', 'PFRPG', 'Savage Worlds', 'Universal')."New value: +"Ruleset code, from list_rulesets."
    • changedInput schema / properties / type / description
      Previous value: -"Item type (substring, case-insensitive). Vault item types are ruleset-specific strings. Common 5e / 5e24 examples: 'Weapon', 'Armor', 'Tool', 'Adventuring Gear', 'Wondrous Item'."New value: +"Item type (substring, case-insensitive). Vault item types are ruleset-specific strings; an unfiltered search shows the types a ruleset's catalog uses."
  4. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral detail beyond them: the default response is a compact shape, `detail: 'full'` inflates it inline, and passing a Character changes which records appear. It does not mention pagination limits or result counts, but those are covered elsewhere.

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?

Two sentences, front-loaded with purpose then the response-shape default. The parenthetical field list is dense but functional; there is no filler.

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 9-parameter search tool with an output schema and full annotation coverage, the description supplies what the structured data cannot: the default response shape and the filtering side effect of the character parameter. Nothing critical to correct invocation 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 baseline is 3, but the description still adds meaning the schema lacks: it enumerates what the summary shape actually contains and explains the summary-vs-full tradeoff in terms of payload size. The remaining parameters are left entirely to the schema.

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 states a specific verb and resource ('Search the item library') and defines scope precisely ('stock items plus their own house items'). It does not explicitly contrast itself with vault_get_item or the other vault_search_* siblings, so the differentiation is implied by the resource name rather than spelled out.

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?

It gives clear when-to-use context ('locate an item by name, type, or ruleset') and flags the character-scoped case where results are filtered. It stops short of exclusions, e.g. it never says to prefer vault_get_item when an id is already known.

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