Retrieves cached game state, including your hand, public information, pending options, and available actions, while keeping opponent hands and the deck hidden.
读取缓存的牌局、自己的手牌、公开信息、待选项及当前可用动作。不会暴露对手手牌或牌堆。
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint=true already covers the safety profile, so the description's contribution is the visibility boundary: it states opponent hands and the deck are NOT exposed, and that the data is cached. That is genuine added context an agent needs to interpret results and avoid attempting to read hidden information.
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?
Two short sentences with zero waste: first enumerates what is returned, second states the exclusion. Front-loaded with the resource and the most decision-relevant item (available actions).
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?
There is no output schema, and the description effectively substitutes for one by listing the returned fields — hand, public info, pending choices, actions — plus the explicit non-returned fields. For a zero-param cached-state read tool, an agent has everything needed to call and interpret it.
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?
Zero parameters, so there is nothing to disambiguate; the schema and description are consistent. Baseline applies, and the description instead spends its words on the return payload, which is the more useful investment here.
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?
Specific verb (读取) plus a concrete enumerated resource set: cached table state, own hand, public info, pending choices, available actions. An agent immediately knows what it gets. It does not explicitly contrast with any sibling tool, which keeps it at 4 rather than 5.
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?
Usage is implied — the mention of '当前可用动作' (currently available actions) signals this is the read-before-act tool that feeds the many action siblings (play_cards, draw_card, respond_cha, etc.), but the description never states when to call it or that it should precede an action.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.