Trnch on Elysium

Sell a token

trnch_sell

Build a sell for USDC in one call: give token, and percent of the wallet balance (read on chain) or an exact amount. Quotes three routers and returns the best route as a transaction to sign. The Trnch fee is already deducted from the quote; the rate applied is returned as feeBps. Returns { router, feeBps, quote, approval, tx, chainId, from }: approval, when not null, has to be sent before tx, from the same wallet (chainId 99901). Nothing is sent by Trnch. Errors: 503 while the fee recipient is not configured on this chain (nothing is built), 404 no route, 429 rate or build limit (retry-after). Requires an API key (created by wallet signature), sent as Authorization: Bearer .

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": {
      "token": "<token>"
    },
    "name": "trnch_sell"
  }
}

Input Schema

Name	Required	Description
`token`	Yes	Token to sell, as an address.
`amount`	No	Exact amount in token units, e.g. 1234.5. Capped at the balance. Use this or percent.
`percent`	No	Share of the wallet balance to sell, 100 = all. Use this or amount.
`slippageBps`	No	Max slippage in basis points (100 = 1%). Default 100.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A3.8/5.0

Behavior5/5

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

Goes well beyond the annotations (readOnly=false, openWorld=true, destructive=false) by disclosing that the fee is pre-deducted and surfaced as feeBps, that approval must be sent first from the same wallet on chainId 99901, that Trnch sends nothing, and by enumerating 503/404/429 failure semantics including retry-after. It also states the auth requirement (API key created by wallet signature, Bearer header). This is rich disclosure an agent cannot get from structured fields.

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 core action and outcome, then layered detail (fee, return shape, approval ordering, errors, auth). Every sentence carries useful information, though the middle sentences are densely packed and the response-field discussion runs long compared with the sibling-call guidance that is absent.

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?

Strong on the build/return/error/auth side, which compensates for having no output schema. The notable gap is relative to its siblings: with trnch_quote, trnch_confirm and trnch_check in the catalog, the definition never explains the handoff between quoting, building, signing and confirming, which is the main thing an agent needs to sequence correctly.

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 description coverage is 100%, so the schema already carries the meaning of token, amount, percent and slippageBps. The description adds only marginal semantics beyond it: that the balance is read on chain, and that amount is capped at the balance (the cap is also in the schema). Baseline 3 is appropriate.

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?

States a concrete verb+resource ('Build a sell for USDC') plus the mechanism (quotes three routers) and the artifact returned (a transaction to sign). Explicitly notes 'Nothing is sent by Trnch', which separates it from an execution/confirmation tool. It never names a sibling such as trnch_quote, so sibling differentiation is implied 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?

Gives real guidance on the parameter fork ('percent of the wallet balance (read on chain) or an exact amount') and on sequencing the approval before the tx. However, there is no explicit when-to-use-this-vs-alternative guidance, e.g. when an agent should call trnch_quote instead of building a sell, or how this relates to trnch_confirm.

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

All Trnch on Elysium 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?