Pay-per-call API for AI agents on Base via x402: best-execution swap quotes (~91ms, block-stamped, expiring), contract safety verdicts before an agent approves a token, and a smart-wallet signal feed. Tools: flow_quote, flow_health. No API keys; each call settles in USDC on Base.
Scored across 2 tools
flow_health and flow_quote serve clearly distinct purposes: one checks API status and sync state, the other retrieves a best-execution swap quote. There is no overlap or ambiguity in which tool to use for a given task.
Both tools use the same predictable pattern: a flow_ prefix followed by a snake_case noun/action. The naming convention is consistent and readable.
With only 2 tools, the set is quite thin even for a narrow quote API. Both tools earn their place, but the surface feels minimal rather than comfortably scoped.
For a read-only quote service, health and quote operations cover the core workflow. Minor gaps like supported-token discovery or configurable slippage details can be worked around or may be handled inside the quote response.
Check the Flow quote API health: status, chain, and latest synced block number.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden, but a zero-parameter health check is a low-risk read and the description does convey what it returns (status, chain, latest block). It omits any auth requirements, rate limits, or failure semantics, so it adds only modest context.
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?
A single front-loaded sentence with the action first and the returned fields listed after; every clause earns its place with no 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?
For a zero-param, no-annotation read tool this is nearly sufficient, and the three named return fields compensate for the absent output schema. It could still say what shape/format those fields come back in, so it is not fully complete.
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?
There are zero parameters, which is the baseline-4 case; nothing about parameter semantics needs explaining and the description does not introduce confusing pseudo-parameters.
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 (Check) and resource (Flow quote API health) and enumerates what is returned (status, chain, latest synced block number). The distinction from flow_quote is implied by 'health' rather than stated explicitly, so it stops short of full sibling differentiation.
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?
A health-check tool's usage is largely self-evident, and 'Check the ... API health' implies you call it to verify the API is operational. However, there is no explicit when-to-use or when-not guidance, nor any mention of flow_quote as the alternative for actual quote retrieval.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a best-execution swap quote on Base. Compares Uniswap V3, PancakeSwap V3 and Aerodrome (plus two-hop routes via WETH), returns the winning venue, expected output, edge in bps vs the baseline, a liquidity flag (deep/watch/thin), the exact block number and timestamp, and build latency. Read-only: no funds move.
| Name | Required | Description | Default |
|---|---|---|---|
| chainId | No | Chain id, defaults to 8453 (Base) | |
| tokenIn | Yes | Input token contract address on Base (e.g. USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA4E46E) | |
| amountIn | Yes | Human-readable input amount, e.g. "10" for 10 USDC | |
| tokenOut | Yes | Output token contract address on Base (e.g. WETH 0x4200000000000000000000000000000000000006) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does well: it declares read-only/no-funds-move safety, the venues compared, that two-hop routes are included, and how freshness is conveyed (exact block number and timestamp). It omits error/fallback behavior when no route exists and gives no hint about caching, rate limits, or whether the quote is indicative vs executable.
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?
Front-loaded with the core purpose, then a compact enumeration of return fields and the read-only guarantee. The long second sentence is dense but nearly every clause maps to a real output field; nothing is padded.
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 must describe returns and does so exhaustively: winning venue, expected output, edge in bps vs baseline, liquidity flag (deep/watch/thin), block number, timestamp, and build latency. Combined with the venue list and read-only statement, an agent has everything needed to call and interpret this 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 coverage is 100%, with each of the four parameters (including the chainId default of 8453) documented in-schema, so the baseline is 3. The description only reiterates 'on Base' and adds no format, unit, or constraint detail 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?
States a specific verb and resource ('Get a best-execution swap quote on Base') and immediately scopes the mechanism (Uniswap V3, PancakeSwap V3, Aerodrome, two-hop via WETH). It is trivially distinguishable from the only sibling, flow_health, which is a health check. No ambiguity about what the tool returns.
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?
Usage is implied rather than stated: an agent can infer this is the pricing/quoting call, and 'Read-only: no funds move' signals it is safe to call freely. However there is no explicit when-to-use, no mention of when the quote should not be trusted (stale block, thin liquidity), and no routing to an execution counterpart.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
flow_healthflow_quote
Add one secure layer between your agents and this server.