SiteCheck Agent Intel & Dev

Compares the runtime bytecode of two Ethereum contracts you

agent_intel_bytecode_similarity_radar

Read-only

Compares the runtime bytecode of two Ethereum contracts you name: the share of shared PUSH4 function selectors (Jaccard) and the cosine similarity of their opcode frequencies, combined into one 0 to 1 score with a SIMILAR, PARTIAL or DIFFERENT label. It compares two addresses only; it has no database of known scam or exploit templates, so it cannot say a contract is a known clone. Related tools on this server, for a different need: agent_intel_news_radar when you need latest BBC News headlines from one section feed; agent_intel_stablecoin_peg_integrity_radar when you need current USD price and deviation from the $1 peg for USDT. Price: $0.003 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

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": {
      "a": "<a>",
      "b": "<b>"
    },
    "name": "agent_intel_bytecode_similarity_radar"
  }
}

Input Schema

Name	Required	Description	Default
`a`	Yes	First contract address 0x... (40 hex)
`b`	Yes	Second contract address 0x... (40 hex)

Output Schema

Name	Required	Description	Default
`a`	No
`b`	No
`note`	No
`label`	No
`score`	No
`bytesA`	No
`bytesB`	No
`source`	No
`checkedAt`	No
`selectorsA`	No
`selectorsB`	No
`opcodeCosine`	No
`selectorJaccard`	No
`sharedSelectors`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations only cover readOnlyHint and openWorldHint; the description goes well beyond them by disclosing the pricing model ($0.003 USDC per successful call, x402 across Base/Solana/Arc) and that failed calls are not charged. It also pre-empts a likely misuse by stating up front that no template database exists, so an agent will not over-interpret a DIFFERENT label as a scam verdict.

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?

The metric definition and output format lead, followed by the limitation and then cost, which is good front-loading. The related-tools sentence consumes length on news headlines and stablecoin peg checks that are irrelevant to bytecode comparison, which is the one clearly unearned part.

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

Completeness5/5

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

With an output schema present, return values need no prose, and the description still covers method, output interpretation, chain scope, absence of template data, and payment terms. Nothing an agent needs in order to decide whether to call it, or to invoke it correctly, is missing.

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% and both parameters already document the 0x... 40-hex address format, so the description's 'two Ethereum contracts you name' adds little beyond scope confirmation. Per the baseline rule, 3 is correct when the schema carries the parameter documentation.

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 (compares runtime bytecode of two Ethereum contracts) and distinguishes itself from every sibling by naming the exact metrics: Jaccard share of shared PUSH4 selectors plus cosine similarity of opcode frequencies. It also names the output shape (0-1 score with SIMILAR/PARTIAL/DIFFERENT), so an agent knows both what it does and what it returns.

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?

Explicit exclusion is given: it compares two addresses only and cannot confirm a contract is a known clone because it holds no scam/exploit template database. That is genuine when-not guidance. The cited alternatives (news_radar, stablecoin_peg_integrity_radar) are unrelated to this task, though, and it never points to the actual adjacent tool for the clone question, agent_intel_known_scams_blacklist_db.

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

All SiteCheck Agent Intel & Dev tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?