propose_deal

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 richly: it lists what gets refused (non-positive/non-integer amounts, over-budget amounts, off-catalog cities), the Declaration of Friendship gate for lump-sum gold, the 30-turn timed-item length, and that measured effects are reported with nothing to poll afterwards.

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?

Dense and long, but the core action is front-loaded in the first sentence and the rest is load-bearing detail rather than filler. It could be trimmed (e.g. the parenthetical about Brave New World rules), so it is efficient but not maximally tight.

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?

Despite no output schema, the description explains the reported effects (gold, gold/turn, happiness, per-resource import/export before vs after) and the full item rule set. For a 3-parameter mutation with zero schema documentation, nothing an agent needs to call it correctly appears to be 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?

Schema coverage is 0% and the schema is essentially bare (items is an untyped object array), so the description must compensate. It enumerates every item type with their sub-fields, explains from_us as the direction selector, and defines ask_counter=true as returning counter.items that can be fed straight back.

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?

Opens with a specific verb+resource ("Offer a trade to another civ") and then distinguishes itself from the answering siblings by explaining that the counterpart seat replies with accept_deal / refuse_deal. The two-seat behavior (AI vs human) further separates it from generic diplomacy tools like negotiate_deal.

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 concrete prerequisite ("Read trade_catalog(player_id) first") and states the conditions that change behavior (human seat → pvp/pending; ask_counter=true → counter-offer). It never explicitly says when to prefer this over negotiate_deal, so it falls short of full when/when-not routing.

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