Highwire

Build a transfer (unsigned)

build_transfer

Build an unsigned SOL or higher.fun coin transfer from one wallet to another for signing with your own wallet tooling; no sign URL is generated.

Instructions

Build an unsigned transaction that sends SOL, or a higher.fun coin, from a wallet to another wallet. It has no sign_url: highwire.fun's sign page never signs transfers, since a link can come from anyone. Sign it with your own wallet tooling, or use execute_transfer with the local signer, which only sends to the policy's allowlist.

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": {
      "wallet": "<wallet>",
      "to": "<to>"
    },
    "name": "build_transfer"
  }
}

Input Schema

Name	Required	Description
`to`	Yes	The recipient's wallet. It must be on the policy's transfer_allowlist.
`sol`	No	SOL to send. Give this, or mint and tokens.
`mint`	No	A higher.fun coin to send instead of SOL.
`tokens`	No	Whole tokens of `mint` to send.
`wallet`	Yes	The wallet that sends and pays (public key only).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false, but the description adds the crucial behavioral fact that the output is unsigned and deliberately unsignable via the hosted sign page for trust reasons. It does not cover transaction expiry, fee payer details, or whether repeated calls produce differing transactions, so it stops short of full disclosure.

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?

Three sentences, front-loaded with what is built, then the no-sign_url rationale, then alternatives. Every sentence carries information, though the middle sentence is dense and uses the alternate name 'highwire.fun' where the ecosystem is called higher.fun, which briefly distracts.

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?

This is a write-path construction tool with no output schema, so the description should say something about what comes back (an unsigned transaction blob) and how to sign and broadcast it; it only gestures at 'your own wallet tooling'. Nothing is wrong, but an agent is left guessing about the return payload and submission flow.

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 each parameter (wallet, to, sol, mint, tokens) is already documented with patterns and bounds; the baseline of 3 applies. The description restates the SOL-or-coin choice and that the wallet both sends and pays, adding little beyond the schema, and does not clarify that sol is mutually exclusive with mint/tokens.

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

Purpose5/5

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

States a specific verb and resource ('Build an unsigned transaction that sends SOL, or a higher.fun coin, from a wallet to another wallet') and implicitly separates itself from build_trade and execute_transfer. An agent can tell this is transaction construction, not submission, without opening the schema.

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?

Explicitly explains there is no sign_url and why, then gives two alternatives: sign with your own wallet tooling, or use execute_transfer with the local signer subject to the allowlist. Clear routing guidance, though the boundary with build_trade (swap vs transfer) is only implied, and the claim that execute_transfer 'only sends to the policy's allowlist' sits oddly against the schema's requirement that `to` already be on transfer_allowlist.

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