evm_balanceExperimental (outside the core SEC path; not covered by the published accuracy eval, may change or be withdrawn): Native balance of any 0x address with block height, from public RPC. Costs $0.01 per call.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | No | base or ethereum. Default base. | |
| address | Yes | 0x-prefixed address. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint and openWorldHint annotations already covering safety, the description adds valuable context: experimental status (outside SEC eval, may change), cost ($0.01 per call), and data source (public RPC). These disclose operational traits beyond annotations without contradiction.
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 with the experimental caveat front-loaded, followed by the core function and cost. It is efficient, with no redundant phrases, though the caveat is slightly lengthy. Structure is logical and scannable.
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 2 params and no output schema, the description covers essential operational context: experimental status, cost, data source, and the inclusion of block height in the response. It does not specify balance units (e.g., wei), which is a minor gap but acceptable given the simplicity.
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?
Schema coverage is 100% with both params described (chain and address). The description does not add new parameter semantics beyond the schema, so baseline 3 is appropriate. The mention of 'block height' describes output, not a parameter, and is a minor addition.
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: retrieving the native balance of any 0x address on Base or Ethereum, with block height, from public RPC. This distinguishes it from siblings like evm_gas (gas prices) and token_price (token balances) by focusing on native balance and chain specificity.
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 usage: use this for native balance on Base/Ethereum, but it does not explicitly contrast with sibling tools (e.g., token_price for token balances) or state when not to use it. It provides context but lacks explicit routing to alternatives.
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 have clearly written descriptions, but several pairs overlap semantically: token_price/token_report, latest_filings/recent_filings, and institutional_holdings/who_holds/activist_stakes all require careful reading to pick the right one. The overlap is not severe enough for a 2, but it is still more than the occasional confusion.
Names are consistently snake_case and mostly descriptive, but the set does not follow one naming convention. It mixes noun phrases (crop_data, token_report, insider_trades) with verb phrases (lookup_company, compare_filings, verify_financial_claim), and pairs like latest_filings/recent_filings create avoidable confusion.
31 tools is too many for what is nominally an SEC Filings server, and the scope sprawls into unrelated domains such as EVM gas, tokens, prediction markets, crop data, and x402 auditing. The count does not feel earned by a coherent workflow; it feels like an uncurated bundle of endpoints.
The SEC filing workflow is reasonably covered: company lookup, search, latest/recent filings, section extraction, 8-K events, comparisons, ownership filings, and XBRL financial checks are all present. However, there is no full-filing retrieval endpoint, no deep company financial history beyond a single concept, and many non-SEC subdomains are only one-off data points, so the overall surface is still incomplete.