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

Annotations already declare destructiveHint=true; description adds the key behavior that it replaces the entire current list (providing the empty-array-to-clear hint). It also discloses the secure-split read-only restriction, which is valuable operational context beyond annotations. Minor gap: doesn't mention whether changes are reversible or any confirmation/response behavior, but given existing annotations the bar is lower.

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?

Three tight sentences, all earning their place. Front-loads the purpose, adds the replacement behavior, then the scope restriction. Zero filler or redundancy.

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 mutation tool with destructiveHint, the description thoroughly covers purpose, scope limits, and the critical empty-array-to-clear behavior. It notes the tools applies only to simple splits, which is essential for an agent choosing among 11 siblings. Output schema exists, so return format needs no explanation. Minor gap: doesn't mention maxItems=8 limit but that's captured in schema.

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 already explains 'split', 'value', and 'participant' at 67% coverage. Description adds meaning beyond schema: clarifies methods array can be empty to clear, explains the replace-semantics, and connects methods to the broader purpose (QR code/pay link). The 'value' parameter's format is fully documented in schema, so little added here, but the array-replacement semantics is meaningful added value.

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?

Description clearly states verb+resource+effect: 'Set how a participant wants to be paid back' and explicitly notes the consequence ('so the split can show a QR code or pay link'). Differentiates from siblings by specifying it works only on simple, accountless splits and that it replaces the current list.

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?

Provides explicit when-to-use rationale (to enable QR code/pay link display), and clearly states exclusions: secure splits are read-only and must be opened in a browser. This effectively tells the agent when NOT to use this tool among sibling tools like record_payment or update_split.

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