Skip to main content
Glama

Ellimist

Swap / bridge quote

exchange_quote
Read-only

Best route to convert any token to any token across chains: output, minimum output, fees, gas, time; with 'alternatives', other routes to compare. Sanctions-screened. Ellimist fee: 0.25% of volume, at least $0.05 and never more than 1%. Conversions are executed by third-party smart contracts (routed by LI.FI) that may fail or be exploited; funds may be lost and transactions are irreversible. Price: $0.005 USDC per call via x402 (no account). Not charged if it fails.

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": {
      "from_chain": "<from_chain>",
      "to_chain": "<to_chain>",
      "from_token": "<from_token>",
      "to_token": "<to_token>",
      "from_amount": "<from_amount>",
      "from_address": "<from_address>"
    },
    "name": "exchange_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault
orderNoCHEAPEST
slippageNo
to_chainYes
to_tokenYessymbol (ETH) or token address
from_chainYes
from_tokenYessymbol (USDC) or token address
to_addressNo
from_amountYesamount in the token's smallest unit
alternativesNoalso return up to this many alternative routes
from_addressYes
allow_high_impactNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior5/5

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

The description adds substantial behavior beyond the readOnlyHint/openWorldHint annotations: sanctions screening, a tiered fee (0.25% of volume, floor $0.05, cap 1%), x402 per-call pricing with a failure waiver, third-party routing via LI.FI, and explicit warnings that routed contracts may fail or be exploited with irreversible fund loss. That is exactly the kind of cost and risk context annotations cannot carry. The loss/irreversibility warning concerns the downstream conversion rather than this quote, but it is framed as such and does not conflict with readOnlyHint.

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?

Front-loaded with the primary outcome and return fields, then fees, then risk, then pricing, so an agent can stop reading early. The first sentence is a long semicolon-and-comma chain that takes effort to parse, but nearly every clause carries decision-relevant information and there is no filler.

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

Completeness4/5

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

For a read-only quote tool with no output schema, the description covers the important ground: it enumerates return fields (output, minimum output, fees, gas, time, alternatives), discloses full cost structure, and flags counterparty risk. The remaining gap is semantic coverage of routing/risk parameters like order, slippage, and allow_high_impact, which an agent needs to tune the quote correctly.

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

Parameters2/5

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

With 11 parameters and only 36% schema description coverage, the description should compensate more than it does. It clarifies 'alternatives' (additional routes to compare) and the shape of the response, but leaves 'order' (CHEAPEST/FASTEST), 'slippage' (default 0.005), 'allow_high_impact', and the null-default 'to_address' entirely unexplained, which are the parameters most likely to produce a bad quote if misunderstood.

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 opening clause names a specific verb and resource: it returns the best route to convert any token to any token across chains, along with output, minimum output, fees, gas, and time. That makes it legible as a read-only quoting tool rather than an execution tool, and the note that conversions are executed by third-party contracts reinforces this. It stops short of naming the natural counterpart (exchange_build_swap), so sibling differentiation is implied by behavior rather than stated.

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

Usage Guidelines3/5

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 pre-execution quoting step because the description explains returned route fields and the 'alternatives' comparison option. However, it never says 'use this before exchange_build_swap' or when-not to call it, and offers no guidance against the other exchange_* siblings. The billing note ('$0.005 USDC per call, not charged if it fails') is the only concrete decision input provided.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources