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

Annotations only declare it is not read-only, not destructive, and not open-world; the description adds genuine value by disclosing escrow behavior ('The teacher holds your side until they answer'), telling the agent the offered assets are locked pending a response. It still doesn't say whether a declined offer is refunded, whether items are validated as owned, or whether multiple pending offers can coexist.

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?

Two tight sentences with the action and the escrow consequence front-loaded, no wasted wording. The playful 'kid/teacher' framing conveys the model domain but slightly blurs precise operational detail.

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?

For a five-parameter mutation with no output schema, the description covers the core concept and the pending-state mechanic but omits the resolution path (accept/reject, refunds) and any ownership or validation rules. An agent knows roughly what the call does but not what state it leaves behind.

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 60% (the two coin amount fields are undocumented), so the description partially compensates by framing the fields as 'your' versus 'theirs'. However it never clarifies the give/want pairing rules, whether both sides may be empty, or what the coin caps mean, leaving the two undocumented numeric parameters ambiguous.

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?

The description states a specific verb and resource ('Offer another kid a swap') and enumerates the exchange shape ('some of your coins or a treat, for some of theirs'). The phrase 'until they answer' gestures at a counterpart tool (answer_trade) without naming it, so the sibling differentiation is implied rather than explicit.

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: 'The teacher holds your side until they answer' conveys that this is the initiating half of a two-step flow, but the description never says when to use this versus answer_trade, nor what to do if the other kid declines. An agent must infer the workflow from narrative flavor text.

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