Address funding payments or ledger updates

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

Annotations already declare readOnlyHint=true and openWorldHint=true, but the description adds meaningful behavior: page sizes (50/page ledger, 100/page funding), the 2000-row cap, maxPages follow-through, and nextStartTime continuation. Crucially it warns that totals cover ALL matched rows and must be quoted rather than re-summed, preventing an aggregation error. Auth/rate-limit context is absent, so it falls short of a 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?

It is front-loaded with the tab scope and default kind, then layers pagination and totals semantics efficiently in a dense telegraphic style. The heavy abbreviations (timeIso, coveredRange, nextStartTime) are compact but assume familiarity, slightly reducing readability.

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?

With no output schema, the description carries the return burden well by naming the totals fields (byType {count, sumUsdc, inUsdc, outUsdc} for ledger, {netUsdc, paidUsdc, receivedUsdc, byCoin} for funding). Combined with pagination caps, continuation logic, and the totals-must-be-quoted rule, an agent has what it needs to call and interpret results correctly.

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 100%, so the schema already documents all nine parameters, including kind's default, startTime's per-kind defaults, and maxPages' default of 5. The description largely restates those same defaults rather than adding new syntactic or format meaning, so the baseline 3 applies.

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 names the specific resource ('Funding' / 'Ledger' tabs) and the row shape (timeIso, newest first), so the agent knows this returns address funding/ledger activity. It doesn't explicitly differentiate from close siblings like flowscan_address_fills, flowscan_address_orders, or flowscan_address_extras, leaving the agent to infer the boundary from the tab names.

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?

It gives usable context for the internal choice: kind='ledger' (default) covers deposits/withdrawals/sends/transfers/vault-staking moves, while kind='funding' covers hourly payments, with distinct default windows. However, there is no guidance on when to prefer this tool over any sibling (fills, orders, staking, extras), so routing to alternatives is left to inference.

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