Preflight and broadcast an already-signed EVM transaction. Disabled unless ALLOW_EVM_BROADCAST=true; never signs or stores keys.
| Name | Required | Description | Default |
|---|---|---|---|
| confirmation | Yes | ||
| rawTransaction | Yes | ||
| expectedChainId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds important behavioral context beyond annotations: it states the tool is disabled unless a specific environment variable is set, and it explicitly says 'never signs or stores keys.' This is valuable because the annotations already indicate destructiveHint=true and readOnlyHint=false, but the description clarifies the safety aspect regarding key handling. It does not contradict annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the main purpose, and includes a critical usage condition and a safety note. Every sentence earns its place; no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (broadcasting a real transaction) and the lack of an output schema, the description covers the essential points: what it does, the preflight aspect, the environment variable gate, and the key-handling safety. It could have mentioned that the transaction must be signed and that broadcasting is irreversible, but the destructiveHint annotation already covers irreversibility. Overall, it's fairly complete for a tool with this schema richness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, so the description must compensate. The description does not explain the parameters (rawTransaction, expectedChainId, confirmation) beyond what the schema provides. The confirmation parameter's const value is self-explanatory, but the description could have added context about expectedChainId's purpose (e.g., to prevent replay attacks). Since the schema already defines the parameters with types and constraints, the description adds minimal value here.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Preflight and broadcast an already-signed EVM transaction.' It uses a specific verb ('broadcast') and resource ('already-signed EVM transaction'), and distinguishes it from siblings like evm_call and evm_estimateTransaction by focusing on broadcasting a signed transaction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions a critical usage condition: 'Disabled unless ALLOW_EVM_BROADCAST=true.' This tells the agent when the tool is available. However, it does not explicitly state when to use this tool versus alternatives like evm_estimateTransaction for preflight, though the purpose implies it. It also doesn't mention that the transaction must be signed, which is implied by 'already-signed'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool is clearly scoped to a specific chain (btc_ vs evm_) and action (broadcast, decode, estimate, get, call, read). There is no overlap or ambiguity between tools, and even similar-sounding operations like evm_call, evm_readContract, and evm_estimateTransaction are distinct in their purpose and input requirements.
All tools follow a consistent snake_case pattern with chain prefix (btc_ or evm_) followed by a descriptive verb and noun (e.g., btc_getBlock, evm_getLogs). The naming is uniform across both chains, making it predictable and easy to navigate.
At 18 tools, the server sits in the 16-25 range which is considered heavy per the rubric. While the count is justifiable given the dual-chain scope, it could be trimmed or grouped further. It doesn't feel overwhelming, but it's above the typical well-scoped range.
The server covers the essential read and write operations for both Bitcoin and EVM chains, including balances, blocks, transactions, gas estimation, contract reads, and transaction broadcasting. No critical gaps are apparent for a chain RPC server, and all common workflows are supported.