city_screen

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

With no annotations, the description carries the full burden and does substantial work: it discloses the buyable vs buy_gold/can_afford:false red-pricing distinction, can_sell/sell_gold/gold_maintenance on sellable buildings, worked_by for tiles another city owns, and blockaded/enemy markers. The trailing note that writes are separate tools implies this call is read-only, which is important context. It stops short of 5 because it never explicitly states the call has no side effects.

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?

It is long but information-dense: nearly every clause maps to an actual field in the return payload (meters, breakdown, yields, buyable, worked_by, can_sell), which is necessary since no output schema exists. It is front-loaded by starting with what the screen contains, though the single undifferentiated paragraph reduces scanability.

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?

There is no output schema, so the description must explain returns, and it does so thoroughly, covering meters/breakdown, specialists, worked tiles, buyable plots, sellable buildings, and the write-tool pointers. The remaining gap is call-side guidance (parameter format and when to choose this over sibling reads).

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 single param `city_id` has 0% schema description coverage, so the description must compensate. It conveys that the tool is scoped to 'one of my cities', which indirectly explains the argument, but it never states format, valid range, or how to obtain the id (e.g. from `cities`). Marginal value over the schema.

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: it is the read-only view of one city's screen, and it enumerates exactly what the payload contains (buildings, specialists, worked tiles, production queue, focus, buyable plots). An agent immediately understands it returns city-state data. It does not name a sibling like `cities` or `compare` to differentiate scope, so it stops short of a 5.

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?

Usage is only implied: this is the screen to inspect a city's full status. It helpfully notes that writes from the same screen live in separate tools (set_city_focus, buy_city_plot, etc.), which routes the agent away from using this for mutations, but it never states when to prefer it over `cities`, `compare`, or `overview`.

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