Create a new game instance for a given family. Returns initial state to pass to subsequent calls. Variant can include flags like "grand+random" or "standard+drops".
| Name | Required | Description | Default |
|---|---|---|---|
| family | Yes | Game family name (chess, draughts, go, reversi, shogi, xiangqi) | |
| rngSeed | No | Optional RNG seed for deterministic games | |
| variant | No | Variant slug, optionally with flags (e.g. "grand", "grand+random", "standard+drops") |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It discloses the key behavior of returning an initial state and gives variant flag examples, which is useful. However, it does not mention potential side effects (e.g., whether it affects existing games), prerequisites, or error conditions, leaving some uncertainty about the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core action, and every sentence adds value. No wasted words, and the variant examples are efficiently integrated.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 3-parameter tool with no output schema, the description is reasonably complete: it explains the purpose, the workflow connection (subsequent calls), and provides variant format examples. It does not detail the return data structure or error behavior, but given the tool's simplicity and high schema coverage, it suffices.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Since schema coverage is 100%, the baseline is 3. The description adds meaning by providing concrete examples for the variant parameter ('grand+random', 'standard+drops'), which helps agents understand the expected format beyond the schema's generic description. This elevates it above baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific action 'Create a new game instance for a given family' and clarifies its purpose by noting it 'Returns initial state to pass to subsequent calls.' This clearly distinguishes it from siblings like play_apply_move or play_load_fen, which handle different phases of game interaction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The sentence 'Returns initial state to pass to subsequent calls' gives clear context on how the tool fits into the workflow: it is the starting point for a new game, and its output is intended for use with other tools. However, it does not explicitly state when to use this instead of alternatives like play_load_fen, leaving exclusions unaddressed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clear prefixes (chess_, play_, hex_, oracle_, rpg_, ti4_) that separate concerns, but overlap exists between deprecated chess_* tools and the newer play_* equivalents, plus rpg_random_encounter and oracle_encounter both generate encounters. Descriptions help disambiguate, but the redundancy could mislead agents.
Many tools follow a domain_verb_noun pattern (hex_generate_map, play_get_moves, rpg_search_entities), but there are notable exceptions like dice_roll, game_deck_create, jam_status, and random_player_order that mix noun-first and verb-last conventions. The inconsistent ordering makes it harder to predict tool names.
81 tools is excessive even for a broad games toolkit; the deprecated chess_* tools alone add unnecessary bulk. While the scope is wide, the count exceeds practical limits and could be consolidated into fewer, more focused tools.
The toolkit covers a wide variety of game needs: dice, cards, hex maps, chess, RPGs, TI4, jam management, and galleries. Minor gaps like the score tracker lacking a retrieval method and the absence of some lifecycle operations keep it from being perfect, but core workflows are well covered.
