Skip to main content
Glama

Inspect Evm Interface

inspect_evm_interface
Idempotent

Inspect local flat EVM bytecode without execution or RPC access to decode identities and infer interface candidates; choose raw/hex encoding and complete or summary detail.

Instructions

Inspect explicit local flat EVM bytecode without target execution or chain/RPC access. Select raw or hex encoding explicitly. Omitted or complete detail returns original carrier and decoded identities, full bytecode and all inferred interface candidates inline. For all inferred selectors/offsets/arguments/mutability and identities without bytecode hex or duplicated stdout, select detail: "summary" on this first call: it retains unchanged complete Evidence and returns a distinct linked inspect_analysis_view summary. Read original function rows or bytecode_hex/stdout/stderr text pages using view kind evm and normalized_result.parent_evidence_id; original complete Evidence remains accessible. Bytecode kind, hardfork, deployed authenticity and discovery completeness stay unknown; summary coverage covers only producer-returned candidates. Unchanged bundled EVMole 0.9.3/WASM in an owned bounded worker is initially real-verified on Linux x64; EOF-style EF00 containers are unsupported. No signature lookup, wallet action or transaction broadcast.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "/artifacts/runtime.hex",
      "encoding": "hex"
    },
    "name": "inspect_evm_interface"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute path to caller-selected local bytecode carrier
detailNo
encodingYesRaw bytes or UTF-8 hex with optional 0x prefix and outer ASCII whitespace

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

The description goes well past the annotations, disclosing that no target executes, no signature lookup or wallet/transaction action occurs, that the bundled EVMole 0.9.3/WASM worker is Linux x64 verified, that EOF-style EF00 containers are unsupported, and that bytecode kind/hardfork/deployed authenticity stay unknown. The one gap is that it never states plainly that a summary call persists or links a new evidence record, which is the plausible reason readOnlyHint is false despite the inspection framing.

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 core purpose is front-loaded, but the body is a dense wall of stacked clauses ('without bytecode hex or duplicated stdout', 'unchanged bundled EVMole 0.9.3/WASM in an owned bounded worker') that forces re-reading. Nothing is obviously padding, yet the packing hurts scannability enough that concision-vs-clarity is a real cost.

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 and three parameters, the description carries most of the load and mostly succeeds: it states the returned carriers, decoded identities, full bytecode, and inference candidates, plus explicit unknowns and failure modes. It stops short of describing the summary payload's shape, which an agent must infer from the referenced linked view.

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

Parameters4/5

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

Schema coverage is 67%, and the description genuinely adds meaning where the schema is bare: the detail enum has no schema description, yet the text explains what omitted/complete returns versus what summary returns and when to choose it. Encoding is reinforced but the path parameter gets no added semantics beyond 'caller-selected local carrier'.

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?

The first sentence names a specific verb and resource (inspect local flat EVM bytecode) and immediately bounds it ('without target execution or chain/RPC access'). It also distinguishes its own two modes and names the linked sibling inspect_analysis_view, so an agent can tell it apart from related decode/inspect tools without opening a 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?

It gives conditional steering rather than a vague claim: use detail:"summary" 'on this first call' when you want selectors/offsets/arguments/mutability and identities, and it names the follow-up path (view kind evm plus normalized_result.parent_evidence_id). What it does not do is contrast itself with other sibling tools such as decode_interface_builder, so the alternative-selection guidance is implicit.

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

Deploy Server

Other Tools