settle_ai_rewards

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

Annotations already indicate a non-read-only, non-idempotent operation. The description adds meaningful behavioral details: it validates receipts, publishes one Merkle root, mints rewards, and submits two Base transactions requiring user confirmation. It doesn't disclose whether eligible receipts are consumed or marked settled after the call, which would be useful, but it goes well beyond what annotations provide.

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?

Every sentence earns its place: the first sets the usage gate, the second explains the parameter and operational mechanics, the third addresses confirmation, and the last names the alternative. It is dense, front-loaded, and free of filler.

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?

The description covers the trigger, scope, core behavior, transactions, and alternative. However, there is no output schema, and the description does not state what the tool returns (e.g., transaction hashes, settlement receipt, or confirmation status) or what post-conditions exist on the included receipts. For a multi-transaction settlement action, this is a meaningful 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?

The single parameter maxReceipts is fully documented in the schema with default, minimum, maximum, and a descriptive explanation. The description repeats the default and cap but adds no new semantic meaning beyond 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?

The description uses a specific verb ('settle'/'claim') and clearly identifies the resource: one limited batch of eligible local receipts. It also explicitly distinguishes itself from settle_all_ai_rewards, so an agent can reliably know exactly what scope this tool operates on.

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?

The description opens with an explicit trigger condition: 'Use only after an explicit user request to claim one limited batch'. It also states what it is not for ('not for status or reward previews') and names the alternative for all-pending claims, giving clear when-to-use and when-not-to-use guidance.

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