Address trade fills

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

With readOnlyHint/openWorldHint already covering safety, the description adds substantial behavioral detail beyond annotations: 50/page default, a ~2000-row cap, maxPages follow-through, the `capped`/nextStartTime continuation rule, and the key insight that `totals` aggregates ALL matched fills in coveredRange rather than being a per-row sum.

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?

Extremely dense and front-loaded, leading with what the tool returns before the pagination rules. The telegraphic phrasing (e.g. 'startTime[/endTime]') is compact but slightly compressed, costing a touch of 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?

There is no output schema, so the description carries the return-shape burden itself, listing the row fields and the `totals` sub-structure (count, closedPnlUsdc, fees, volumeUsd, byCoin) plus the pagination edge cases. Nothing an agent needs to call it correctly is missing.

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 coverage is 100%, so baseline is 3, but the description meaningfully extends it: startTime/endTime trigger a different query path, maxPages controls pages past the 2000-row cap (default 5), and aggregateByTime merges partial fills. It adds semantics the schema alone does not convey.

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 ('Address Trades tab: fills') plus the ordering and page size, and enumerates the returned row columns. An agent can distinguish this from flowscan_address_orders or flowscan_address_ledger without opening the 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?

Gives explicit conditional behavior: no startTime returns the latest ~2000 fills, while startTime/endTime switches to the time-range query and follows pages past the cap. It also tells the agent to quote `totals` and never sum rows. It stops short of naming sibling alternatives, so not a 5.

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