reset_predictor

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

With no annotations, the description carries the full burden and does reasonably well: it discloses that all historical frames are destroyed, explains the purpose (avoiding old-trajectory misjudgment), states the return type (确认文本, confirmation text), and specifies the necessary follow-up action. It does not mention permissions, reversibility, or side effects beyond the cleared frames.

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 front-loaded with the core action, then concisely lists usage, parameters, return value, and next step. Every line earns its place, with no redundant or filler text.

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 zero-parameter reset with an output schema, the description supplies everything an agent needs: what it does, when to call it, that it takes no arguments, what it returns, and what to do next. Nothing essential 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?

The tool takes zero parameters, so per the rubric the baseline is 4. The description confirms this with 入参：无, and there is no additional parameter meaning to provide.

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 states a specific verb and resource: 清空预判模块的全部历史帧 (clear all historical frames of the prediction module). This distinguishes it from siblings like clean_cache, which operate on other caches, and names the exact module affected.

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?

It gives explicit triggering contexts: 新开一局、重生、或画面大幅跳变后调用 (call after a new game, rebirth, or large screen jump). It also provides the follow-up step of re-calling perceive_game to accumulate frames. However, it does not state when not to use the tool or an explicit alternative to use instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.