Get post-capture city advice for Civ VI: decide whether to keep, salvage, or raze a newly captured city using loyalty estimates. Call on the capture turn.
占领城市后的处理建议:保留/挽救/夷平,基于忠诚度计算。占城当回合调用。
⚠️ 敌方城市的人口数据无法自动获取 —— 忠诚估算只计入我方压力,结果
偏乐观;若周边敌城密集,把建议降一档理解(保留→挽救,挽救→夷平)。
| Name | Required | Description | Default |
|---|---|---|---|
| city_x | Yes | ||
| city_y | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only say readOnlyHint=true; the description adds a substantive caveat that enemy city population is unavailable, that loyalty estimates only count our own pressure and are therefore optimistic, and tells the agent to downgrade the recommendation one notch when surrounded by enemy cities. This is exactly the kind of output-reliability context an agent cannot infer from structured fields.
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?
Three compact sentences: purpose, timing, then warning. Front-loaded and free of padding; the long caveat is justified because it changes how results should be read, though it could be tightened slightly.
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 purpose, invocation timing, and a critical interpretation caveat. The only real gap is that the two required coordinates are never described in words.
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 description coverage is 0% — only bare titles 'City X' / 'City Y' — so the description must compensate. '占城当回合调用' implies the coordinates identify the newly captured city, but no format, units, or coordinate-system detail is given beyond that implication.
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+resource: advice on what to do with a captured city (keep/save/raze) with loyalty-based computation. It is clearly distinguishable from advisory siblings like get_settle_advisor, get_pillage_advice or assess_loyalty_flip, though it never names those alternatives explicitly.
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?
'占城当回合调用' gives an explicit timing trigger (call on the turn of capture), which is the key usage condition for this tool. It lacks explicit when-not guidance or named alternatives, but the context is clear enough to select it correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.