Skip to main content
Glama

Check code for Zenith gotchas

zenith_check_compat
Read-only

Scans Solidity, TypeScript/JavaScript, or deployed bytecode for Zenith incompatibilities such as block-number clocks, unsupported opcodes, missing dependencies, and RPC limits before deployment.

Instructions

Scans Solidity, TypeScript/JavaScript or deployed bytecode for things that behave differently on Zenith: block.number used as a clock (blocks only come with transactions), prevrandao randomness, blob opcodes, Osaka-only opcodes and compiler targets (Zenith runs Prague), dependencies on Multicall3/Permit2/EntryPoint/CreateX (not deployed), WebSockets, filters and subscriptions (not available), waiting for many confirmations (can hang), and unbounded getLogs ranges.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "zenith_check_compat"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoFile or project folder to scan
sourceNoSource text to scan instead of a path
addressNoDeployed contract to scan by bytecode
languageNoLanguage of `source`solidity

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral context by disclosing the full taxonomy of things it flags, including platform facts (blocks only come with transactions, Zenith runs Prague, no WebSockets/filters, Multicall3/Permit2 not deployed). It does not describe the shape of the report, the severity model, or whether the scan is static-only, so it stops short of full transparency.

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?

A single front-loaded sentence beginning with the verb and object, followed by a dense but purposeful enumeration where each item is a distinct detectable issue. It is long, and a bulleted structure would be more scannable, but there is essentially no filler prose.

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?

Annotations make the safety profile clear and all parameters are documented, but with no output schema the description should say what a scan returns (findings list, severity, locations) and it does not. It also leaves unresolved how the three optional input modes interact when zero or multiple are supplied, which matters for a tool with all-optional parameters.

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 all four parameters are already documented, and the description largely restates the same three input modes (path, source text, deployed bytecode) without adding format or precedence rules. One minor value-add is clarifying the contract surface it understands (Solidity plus TypeScript/JavaScript), but it does not explain that path/source/address are mutually exclusive.

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 (scans) and resource (Solidity, TypeScript/JavaScript, or deployed bytecode), then enumerates exactly what it detects: block.number-as-clock, prevrandao, blob/Osaka opcodes, Multicall3/Permit2/EntryPoint/CreateX dependencies, WebSockets/filters, confirmation waits, unbounded getLogs. None of the siblings (decode, deploy, get_logs, read_contract) overlap with this linting role, so an agent can select it unambiguously.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The nature of the checks implies the tool should be run before deploying or porting code to Zenith, but the description never says so explicitly and never names a sibling as an alternative or a follow-up (e.g. zenith_deploy). Usage is inferred from the enumerated gotcha list rather than stated as when-to-use guidance.

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