FortFi Treasury MCP

propose_swap

Propose an EVM CoW swap. Autonomous agents: fetches and binds a quote inline (default), or pass previewQuoteId from preview_swap_quote for a two-step review. confirm always signs the bound quote — same principle as FortFi Assist. Human session MCP: confirm requires passkey in the app.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "fromWalletId": "<fromWalletId>",
      "sellTokenAddress": "<sellTokenAddress>",
      "buyTokenAddress": "<buyTokenAddress>",
      "sellSymbol": "<sellSymbol>",
      "buySymbol": "<buySymbol>",
      "amountUsd": "<amountUsd>"
    },
    "name": "propose_swap"
  }
}

Input Schema

Name	Required	Description
`amountUsd`	Yes	Sell amount in USD
`buySymbol`	Yes	Human-readable symbol of buy token, e.g. ETH
`sellSymbol`	Yes	Human-readable symbol of sell token, e.g. USDC
`fromWalletId`	Yes	Source wallet id (must be EVM, CoW-supported chain)
`previewQuoteId`	No	Optional — from preview_swap_quote for explicit quote review before propose
`buyTokenAddress`	Yes	Token contract address to buy (0x…)
`slippagePercent`	No	Optional slippage tolerance 0–50 (default 0.5)
`sellTokenAddress`	Yes	Token contract address to sell (0x…)

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 3, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations, the description carries the full load and does add real behavior: quote binding, confirm signing the bound quote, and a passkey requirement in human sessions. However, it never says what propose_swap returns (proposal id? order hash?), whether the proposal expires, or what downstream approval step follows, and the 'same principle as FortFi Assist' reference is opaque rather than informative.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, and the inline-vs-preview distinction follows immediately. The human-session/passkey note is compressed but substantive. The 'same principle as FortFi Assist' clause earns no place, since it references context the agent cannot resolve.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with eight parameters, no annotations, and no output schema, the description explains the quote flow and signing behavior but leaves the proposal lifecycle and return value undocumented. An agent knows how to call it but not what to expect back or what must happen next.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all eight parameters are already documented, including previewQuoteId and slippagePercent defaults. The description reinforces the meaning of previewQuoteId by tying it to preview_swap_quote for a review step, but adds no format or constraint detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence names a specific verb and resource: 'Propose an EVM CoW swap.' The EVM/CoW qualifiers implicitly distinguish it from propose_solana_swap and other propose_* siblings, and the second sentence names preview_swap_quote as the related quote tool. It stops short of an explicit sibling contrast, but an agent can identify the operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly lays out two execution modes: the default inline quote fetch, and the two-step path where previewQuoteId comes from preview_swap_quote. That effectively tells an agent when to call the sibling first. It gives no explicit when-not-to-use guidance or prerequisites beyond the schema's chain/wallet constraint.

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

All FortFi Treasury MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?