assess_attack

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

Annotations only declare readOnlyHint=true, and the description adds genuinely new behavioral rules: values are auto-read from the engine when the city is in sight, city defense cannot be read out of sight, and no green light will be given in that case. It also discloses the decision math (net damage vs 20/turn regen) that explains when a 🔴 verdict is produced.

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 with the verdict tiers and the mandatory pre-war call, which is the right ordering. The Rome/London anecdote is illustrative but adds length that a shorter rule statement could have carried.

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, so return values need not be explained, and the description covers preconditions, visibility constraints, and the verdict semantics well. The remaining gap is the unexplained optional parameters, which for a 7-param tool matters.

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 0%, so the description must carry the parameter burden. It does convey the critical override semantic (engine-read defaults, explicit values take priority, overrides only needed with fresh scouting), but it never explains individual fields such as wall_hp vs wall_max_hp, defense_strength, population, or city_name.

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 ('战前评估:这座敌城能不能打') and immediately names the output shape (four-tier verdict + reasons + alternatives). It is clearly distinguishable from siblings like suggest_siege_plan or get_power_balance because it is a go/no-go judgement on a specific city.

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?

'宣战前必调' gives an explicit mandatory trigger, and the description explains when parameters must be supplied ('only when you have newer scouting intel'). It does not name a sibling alternative (e.g. suggest_siege_plan) for the planning case, so it stops short of full routing guidance.

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