negotiate_deal

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

With no annotations, the description carries the burden and does well: it discloses the non-committal nature, the side effect of closing the trade screen, and what is returned (the AI's reply plus the resulting `items` handed back). It omits auth/permission prerequisites and any failure or refusal behavior, which holds it below 5.

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-loads the core purpose and the no-commitment constraint before the mode breakdown, and the inline JSON example is worth its space. The mode-definition run-on is dense but each clause is functional; minor tightening is possible.

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?

Covers all three modes, the full payload shape, and the return value despite there being no output schema, which is the main completeness risk here. The unexplained `player_id` is the remaining gap.

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%, so the description must compensate and largely does: it defines the three `mode` values and fully specifies the `items` row shape with a concrete JSON example and the meaning of from_us. Only `player_id` is left undocumented.

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 ('ask an AI civ about a deal') and draws the crucial line against committing to it, explicitly contrasting with the sibling propose_deal. An agent can distinguish this from propose_deal/incoming_deal without opening any 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?

Enumerates all three modes with the exact condition that selects each ('equalize': ask what would make a draft acceptable; 'what_will_ai_give': from_us=true; 'what_does_ai_want': from_us=false). It also states the relationship to propose_deal, making the when-to-use decision explicit.

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