SiteCheck Agent Intel & Dev

Heuristic Solidity linter for a snippet or file: unchecked

agent_intel_smart_contract_linter_audit

Read-only

Heuristic Solidity linter for a snippet or file (up to 60000 characters): unchecked low-level call/send/delegatecall, value-sending external calls before a storage write (possible reentrancy), arithmetic under pragma below 0.8.0 (overflow risk), and public or external state-changing functions without a visible owner or sender check, with line numbers. Not an audit; misses most real bugs. Related tools on this server, for a different need: agent_intel_smart_money_inflow_tracker when you need to find the top-ROI accounts on Hyperliquid's public perp; agent_intel_cors_security_misconfig_audit when you need CORS check for a public HTTPS endpoint: three GET requests. Price: $0.004 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": {
      "source": "<source>"
    },
    "name": "agent_intel_smart_contract_linter_audit"
  }
}

Input Schema

Name	Required	Description	Default
`source`	Yes	Solidity source text, 10 to 60000 characters

Output Schema

Name	Required	Description	Default
`note`	No
`counts`	No
`source`	No
`verdict`	No
`findings`	No
`checkedAt`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well past the readOnlyHint/openWorldHint annotations by disclosing pricing ($0.004 USDC per successful call via x402 on Base, Solana or Arc), that failed calls are not charged, the input size ceiling, that results carry line numbers, and an honest accuracy limitation. Payment and billing behavior in particular is information the annotations cannot convey.

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 opening clause is well front-loaded and dense with useful detail, and the pricing sentence earns its place. However, the 'Related tools on this server, for a different need' segment promotes a Hyperliquid flow tracker and a CORS auditor, which are irrelevant to a Solidity linter and dilute an otherwise tight definition.

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?

For a single-parameter tool with a full output schema and read-only annotations, the description covers the checks performed, input limits, billing behavior, and accuracy caveats. Nothing an agent needs in order to decide to call it or interpret its limits 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?

There is only one parameter and schema description coverage is 100%, so the schema already defines 'source' as Solidity text from 10 to 60000 characters. The description's 'up to 60000 characters' merely echoes the schema rather than adding format, encoding, or import-resolution guidance. Baseline 3 for full coverage.

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 ('Heuristic Solidity linter for a snippet or file') and then enumerates the exact four checks performed (unchecked low-level call/send/delegatecall, value-sending external calls before storage writes, pre-0.8.0 arithmetic, missing owner/sender check). This is far more specific than a title restatement and lets an agent know precisely what it gets back.

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 bounds the tool with 'Not an audit; misses most real bugs', which is a genuine when-not-to-rely-on-this caveat, plus a hard input ceiling of 60000 characters. It does not route the agent to a competing linter because none exists among the siblings, but the two sibling callouts it does make are for unrelated needs rather than alternatives to this tool.

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?