ask_questionAsk one yes/no style question about the current puzzle. The AI host answers with one of four judgments: 是(Yes) / 不是(No) / 是也不是(Both) / 没有关系(Irrelevant), plus solve progress (0-100).
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | The question to ask (max 300 chars). | |
| session_id | Yes | Session id returned by start_session. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and discloses the exact response structure: four possible judgments plus a solve progress percentage. It does not mention potential side effects (e.g., whether questions affect score), but for a simple query tool, the disclosure is sufficient and there is no contradiction.
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 sentences, no filler, front-loaded with the verb and object. Every word adds value, and the answer-format list is compact and informative.
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 simple question-asking tool, the description fully covers purpose, expected input behavior, and the response format. The absence of an output schema is mitigated by explicitly listing possible answers. Sibling tools are not confused, and no critical context is missing.
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?
Schema coverage is 100%, with both parameters described in the schema. The description adds only a small contextual hint ('about the current puzzle') for the question parameter, but otherwise repeats schema information. Thus baseline 3 is appropriate.
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 uses a specific verb ('Ask') with a clear object ('one yes/no style question about the current puzzle') and explicitly distinguishes this from sibling tools by focusing on interrogation rather than starting or giving up. The answer-format detail further clarifies its unique role.
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 states when to use the tool (when you need to ask a yes/no question about the puzzle) and the context is clear from the sibling names. It does not explicitly mention exclusions or alternatives, but the purpose is distinct enough that usage is unambiguous.
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.
Each tool serves a unique, non-overlapping purpose: start_session begins a new puzzle, ask_question interacts with the current puzzle, and give_up_and_reveal ends the session by revealing the solution. No ambiguity exists between them.
All tool names follow a consistent verb_noun pattern in snake_case (start_session, ask_question, give_up_and_reveal). The naming is predictable and clearly indicates the action each tool performs.
With only 3 tools, the server is tightly scoped to its purpose. Each tool is essential to the core gameplay loop of starting, playing, and ending a Turtle Soup session, with no unnecessary additions.
The core lifecycle of a puzzle session is covered: start, question, and give-up/reveal. A minor gap is the lack of an explicit 'end_session' or early-quit tool for users who want to abandon a session before reaching the 60 progress threshold, but this appears intentional for game design.