perceive_game

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

With no annotations, the description carries the full burden and mostly meets it: it discloses the multi-frame requirement (≥3) and the graceful-degradation path — service unavailable yields in-process synthetic frames tagged with _fallback and never throws. It does not cover auth, rate limits, or timing costs, leaving minor gaps.

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?

Front-loaded one-line summary followed by clearly labeled 用途 / 入参 / 返回 / 下一步 sections. Every sentence carries distinct information — payload, frame count, fallback behavior, follow-on tools — with no filler.

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?

An output schema exists, yet the description still sketches the return shape (self state + entities list) and the _fallback flag, which is exactly the operationally important part. Combined with the frame-count and degradation notes, nothing an agent needs to call this correctly 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 and the description confirms this ('入参：无'), so there is nothing to disambiguate. Baseline of 4 applies for a no-parameter tool.

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?

States a specific verb and resource ('获取当前游戏画面状态') and enumerates the payload (own HP, nearby entities list). It also positions itself relative to a sibling by naming predict_all_entities as its downstream consumer, so an agent can distinguish it without opening the schema.

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?

Explicit guidance: call 'each decision step before acting', call at least 3 consecutive frames for prediction to be valid, and explicit next steps (predict_all_entities or kb_search). This is the when/when-not/alternatives pattern done well.

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