Skip to main content
Glama

EVM Calldata Decode

evm_decode
Read-only

Decode one EVM calldata hex string. POST JSON data, optional abi, decimals (0-36) and knownSpenders. Matches bundled ERC-20, ERC-721, ERC-1155, ERC-2612, Permit2, Multicall3 and common router selectors, or a caller-supplied ABI. Returns the function, arguments, human amounts when decimals are supplied, and flags for unlimited approval, setApprovalForAll, and a permit spender absent from knownSpenders. No RPC and no selector database. Not a clearance. USDC on Base only. Bad input is not charged. Price $0.01 per call via x402, USDC on Base (MCP payments are Base only). Paid calls are subject to Horizon Pulse buyer terms: https://horizonpulse.dev/terms/buyer

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": {
      "data": "<data>"
    },
    "name": "evm_decode"
  }
}

Input Schema

NameRequiredDescriptionDefault
abiNoOptional function entries, at most 64
dataYes0x-prefixed EVM calldata
decimalsNoInteger 0-36 from the caller. Human amounts use it. Omit to leave amounts raw.
knownSpendersNoAddresses already named as permit spenders, at most 16

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already cover the read-only, non-destructive, closed-world profile, and the description adds substantive behavior on top: no RPC and no selector database (i.e., purely static decoding), bad input is not charged, per-call pricing and payment rails, and the exact flags emitted for unlimited approval, setApprovalForAll, and unknown permit spenders. Nothing here conflicts with the annotations.

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

Conciseness3/5

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

The purpose and decoding coverage are front-loaded and efficient, but the closing sentences are padded: 'USDC on Base' is stated twice, the terms URL and $0.01 price occupy a full sentence, and 'POST JSON data' and 'Not a clearance' are vague filler that does not help invocation.

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?

With no output schema, the description correctly spends words on the return shape (function, arguments, human amounts, flags) — enough for an agent to use results. The main gap is error/fallback behavior: it does not say what is returned when a selector is unknown and no ABI is supplied.

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 the schema already documents all four parameters and the description largely restates them. It does add one piece of functional meaning — that knownSpenders drives the 'permit spender absent from knownSpenders' flag and that decimals produces human-readable amounts — but nothing about abi entry shape or matching precedence beyond the schema.

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?

Opens with a specific verb and resource ('Decode one EVM calldata hex string') and constrains scope to a single input. It then names exactly what selector families are recognized and that a caller-supplied ABI is an alternative path, so an agent knows precisely what this does and that no sibling tool covers calldata decoding.

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?

Gives clear context for use: bundled ERC-20/721/1155/2612, Permit2, Multicall3 and router selectors, with a supplied ABI as the fallback when a selector is not bundled. It does not state exclusions ('when not to use') or point at an alternative tool, and 'Not a clearance' is too terse to function as a real usage boundary.

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.