Most recent swaps executed through Epsilon, optionally filtered to one wallet. Amounts are RAW token units.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | max rows (default 100, cap 500) | |
| wallet | No | optional wallet address to filter by |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint and destructiveHint annotations already establish that this is a safe read operation. The description adds a valuable non-obvious behavioral detail: amounts are in RAW token units. It does not cover pagination or ordering, but the annotations lower the bar and the raw-units note is meaningful.
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 tightly written sentences with the core purpose front-loaded and no filler. The raw-units note is the only extra detail, and it earns its place as important behavioral information.
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 simple read-only tool with two optional parameters and full schema coverage, the description covers the resource, the optional wallet filter, and a key output format detail. Absence of an output schema makes the return shape slightly underspecified, but the definition is still adequate for correct invocation.
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 both parameters. The phrase 'optionally filtered to one wallet' restates the wallet parameter's schema description but adds no new information about formats, defaults, or edge cases.
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 clearly states the resource ('most recent swaps executed through Epsilon') and the optional scope ('filtered to one wallet'). It is specific enough to convey what the tool does, though it does not explicitly name a sibling tool to differentiate from.
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 gives clear context for when the tool is relevant — recent swaps, optionally for one wallet — but provides no explicit guidance about when to use it instead of sibling tools such as list_orders, get_quote, or token_volume. Usage must be inferred rather than instructed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly separated by resource (orders, quotes, routes, tokens, docs, examples), but market_stats, get_market_overview, and token_volume overlap on volume/engine-wide stats, and get_quote/get_route are closely related. Descriptions mitigate most misselection.
Most accessors use get_/list_/search_ verbs, but five tools (error_catalog, market_stats, order_preflight, recent_swaps, token_volume) use bare noun phrases instead of a consistent verb-first pattern. All names are snake_case and readable, so the mixed verbs are a moderate inconsistency.
At 15 tools the server is at the top of the ideal range and each area (market data, orders, quotes/routing, docs, examples) is represented. A few overlapping stats/volume tools make it feel slightly heavier than necessary, but the count is not a problem.
The read-only surface is fairly complete: quotes, routes, orderbook, order status/list, market stats, token search, docs, examples, and error catalog. However, there are no tools to create/submit or cancel orders, and no wallet/balance/allowance tools, so agents cannot complete an actual trade from quote to execution. This is a notable gap if the server is meant to support trading, not just research/development.