Start a fresh game on a named table and return the initial observation for solo or multi-agent turn-based play.
Start a fresh game on a table and return the initial observation.
table names the session so several games can run concurrently (defaults to
the game name). Solo play: just call act() next. Multi-agent play: each
agent calls join() to claim a seat, then loops wait_turn() -> act().
| Name | Required | Description | Default |
|---|---|---|---|
| game | Yes | ||
| table | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. 'Start a fresh game' conveys that reset creates a new session and effectively replaces prior table state, and 'return the initial observation' sets output expectations. It adds session-scoping context via table, though it does not spell out permissions or behavior if the table already has an active game.
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?
Three sentences deliver the core action first, followed by table semantics and then the solo/multi-agent flow. Every sentence contributes actionable information without repetition, and the line break makes the workflow easy to scan.
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?
The definition explains the entry point, return value, table/session scoping, and the exact next tools for solo and multi-agent play, so the agent can call reset correctly. It lacks only minor details like error behavior for occupied tables or an explicit pointer to list_games for valid game names. Given there is no output schema, the 'initial observation' return is stated but not structurally detailed.
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?
The schema provides only types and titles with 0% description coverage, so the description must compensate. It clearly defines table as a session name that defaults to the game name, but game is only indirectly described as the game being started; there are no valid game-name examples or an explicit pointer to list_games for discovery. This is partial but not complete compensation.
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 opening sentence pairs an action verb ('Start a fresh game') with a specific resource ('on a table') and return value ('initial observation'). This clearly differentiates reset from siblings: observe/act/wait_turn operate within an existing game, join claims a seat, and list_games enumerates options.
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 description gives an explicit call sequence: after reset, solo play proceeds to act(), multi-agent play requires each agent to join() then loop wait_turn() -> act(). It also explains when the table parameter matters, so the agent can decide whether to pass it. The workflow guidance is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.