ERC-20 token balance of a holder on Base (formatted + raw).
| Name | Required | Description | Default |
|---|---|---|---|
| token | Yes | ERC-20 contract address on Base: 0x followed by 40 hex characters. | |
| address | Yes | Wallet address whose balance to read: 0x followed by 40 hex characters. |
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?
With no annotations, the description carries the burden. It usefully discloses that both formatted and raw balance values are returned, and 'balance of a holder' implies a read-only query. Yet it does not mention failure behavior for invalid addresses or non-token contracts, nor how decimals/raw values are represented.
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?
A single front-loaded sentence conveys resource, scope, network, and return format with no filler. Every phrase 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 lookup with fully documented parameters, the description plus schema cover the essential details: network, token, address, and return shape (formatted + raw). There is no output schema, so the return hint is valuable and present; a note on decimal handling would make it more complete.
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 already fully documents both parameters with 100% coverage. The description adds only the ERC-20 and holder context, which maps naturally to token and address, but provides no extra semantic details beyond the schema.
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 identifies the resource (ERC-20 token balance), the holder scope, and the network (Base), and the parenthetical 'formatted + raw' signals return format. It is unambiguous, though it lacks an explicit verb like 'get' or 'return', and does not explicitly compare against 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 use case is implied: call this when you need a holder's ERC-20 balance on Base. However, it does not state when to prefer this over token_info or address_report, nor does it mention exclusions or prerequisites, so usage guidance is only implicit.
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 targets a distinct query type: address snapshot, gas price, token balance, token metadata, and transaction status. The only minor overlap is that address_report includes USDC balance, which could also be retrieved via token_balance, but the descriptions make the intended use clear.
All tool names follow a consistent snake_case noun or noun_verb pattern: address_report, gas_now, token_balance, token_info, tx_status. The naming is predictable and clearly indicates the subject and purpose of each tool.
Five tools is well-scoped for a read-only Base chain intelligence server. Each tool covers a meaningful and distinct data need without redundancy or unnecessary bloat.
The set covers the core read-only needs for Base chain data: balances, token metadata, gas, and transaction status. Minor gaps exist such as token transfer history or block details, but the current surface handles common queries without major dead ends.