get_gas_oracleGet current gas price recommendations (safe / propose / fast) from the gas tracker.
| Name | Required | Description | Default |
|---|---|---|---|
| chainid | No | Numeric chain id (e.g. 1=Ethereum, 56=BNB, 137=Polygon). Defaults to server config. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, so the description only needs to add context. It adds that the data is 'current' and sourced from the gas tracker, which aligns with the annotations and gives the agent useful situational awareness.
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 a single sentence that states the action, source, and output categories with no filler. It is front-loaded and every word earns its place.
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?
For a simple read-only tool with one optional parameter and no output schema, the description plus annotations cover the essentials. The only minor gap is exact output units or JSON format, but the named return categories are sufficient for correct invocation.
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 input schema fully documents the only parameter, including pattern, example chain IDs, and default behavior, so the description does not need to repeat it. Since schema description coverage is 100%, the baseline of 3 is appropriate.
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 uses a specific verb ('Get'), names the resource ('gas tracker'), and identifies the exact output categories ('safe / propose / fast'). It is clearly distinct from the many transaction/address/contract sibling tools.
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 implies the tool is for retrieving current gas price recommendations, and no sibling tool covers gas prices, so there is no direct alternative to confuse it with. However, it does not explicitly state when to use it or mention that chainid is optional depending on server configuration.
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.
Most tools target clearly distinct data types: balances, transactions, logs, contracts, tokens, gas, and chains. The main confusion risk is between get_transaction_status, get_transaction_receipt_status, and get_transaction_receipt, which all relate to transaction outcomes and could be easily misselected.
Every tool follows the get_<object> or get_<object>_<qualifier> snake_case pattern. The naming is highly predictable and makes the tool purpose evident from the name alone.
20 tools is on the heavier side, approaching the upper bound for a coherent MCP server. However, given Etherscan's broad read-only domain—addresses, transactions, contracts, tokens, logs, and gas—the count is defensible even if it feels somewhat large.
The toolset covers the major Etherscan data-access patterns: balances, normal/internal transactions, receipts, token transfers, contract ABI/source/creation, logs, and gas. Obvious gaps like fetching a block by number/hash or listing transactions within a block are missing, but agents can accomplish most explorer workflows.