predict_all_entities

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

With no annotations, the description carries the full burden and does so well: it discloses the no-input/history dependency, the max-8 threat-sorted output, the confidence < 0.65 gating rule (prediction_trusted=false, x_predict/y_predict null, 'don't trust it'), and the insufficient_data fallback. These are exactly the edge-case behaviors an agent needs.

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 purpose followed by a labeled 用途/入参/返回/下一步 structure. Slightly long due to the field list, but each block adds actionable information and there is 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?

For a 0-param tool with an output schema, the definition is fully complete: it covers purpose, dependency, next step, the confidence-gating edge case, and the insufficient_data failure mode. Nothing an agent needs to call it 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?

Zero parameters, so baseline is 4. The description reinforces this by explicitly stating '入参：无' and explaining the implicit input dependency (accumulated perceive_game history frames), which the empty schema cannot convey.

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 ('预测画面中全部实体未来约 1.2 秒的位置') with a precise scope (all entities, ~1.2s horizon). It is clearly distinguishable from perceive_game (current-frame perception) and game_action (acting), so an agent can tell these apart without opening a 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?

Gives a clear use context ('判断威胁、决定走位与攻击目标') and the next-step routing to game_action's move/attack. It also flags the prerequisite that the call depends on prior perceive_game history frames. It stops short of stating when not to use it or naming an alternative predictor, so it is not a full 5.

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