Keyless, read-only BNB Chain and Ethereum data: transactions by hash, tokens with a lookalike check
Scored across 2 tools
get_token and get_transaction target completely different resources (a token contract vs a transaction) with no overlap in inputs or outputs. An agent can select between them unambiguously based on whether it has a contract address or a tx hash.
Both tools follow the same clean get_<noun> verb_noun pattern, using snake_case consistently. The convention is predictable and readable.
Only 2 tools for something branded as an 'explorers' server feels thin; explorers typically expose several lookup surfaces. The two present are reasonable, but the set is under-scoped relative to the apparent domain.
There is no address/balance lookup, no address transaction history, no block lookup, and no token transfer listing, which are core explorer operations. An agent asked to inspect a wallet or gather a token's activity has no tool available and would hit a dead end.
A BNB Chain or Ethereum token contract: name, symbol, decimals, total supply, indexed holder count, and lookalike: the well-known token (e.g. USDT) whose name or symbol it imitates, with that token's real contract. lookalike: null only means no match against a short list of well-known tokens; it is not a safety verdict.
| Name | Required | Description | Default |
|---|---|---|---|
| chain | Yes | "bnb" = BNB Chain, "eth" = Ethereum | |
| address | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint, openWorldHint, idempotentHint) already establish the safety and idempotency profile, so the bar is lower, and the description adds a genuinely non-obvious caveat: `lookalike: null` only means no match against a short list of well-known tokens and is explicitly not a safety verdict. That prevents a real misinterpretation. It stops short of disclosing error behavior for malformed or unknown addresses, so it is not a 5.
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?
Two sentences, no filler; the field inventory and the lookalike warning are both load-bearing given there is no output schema. The weak spot is structural rather than length-related: the first sentence is a verbless fragment, so the subject of the sentence is ambiguous on a first read.
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?
With no output schema, the description properly carries the return-value burden and enumerates the returned fields plus the important lookalike semantics. What is missing is the framing action (what the tool does with chain + address) and failure behavior for unknown or malformed addresses, which is why it falls short of 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?
Schema coverage is 50%: `chain` has an enum description in the schema, but `address` is documented only by a regex pattern with no prose. The description mentions no parameters at all — not the accepted chain values, not the required 0x address format — so it does not compensate for the coverage gap. The 3 baseline applies only when the schema already does the heavy lifting.
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 is a noun phrase listing the fields of a token contract ('name, symbol, decimals, total supply, indexed holder count, and lookalike') rather than stating the action. The resource (a token contract on BNB Chain or Ethereum) is identifiable, and the sibling get_transaction is implicitly distinguished by resource type, but no verb ('returns'/'looks up ... for the given address') is supplied, so the purpose must be inferred from the name and title.
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?
There is no statement of when to call this tool, no prerequisites, and no mention of the sibling get_transaction as an alternative. The only guidance-like content is the caveat about what `lookalike: null` does not mean, which is a behavioral note rather than usage routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
One BNB Chain or Ethereum transaction by hash: from, to, value (wei), gas, status. Recent transactions come from the explorer index; older ones are read from the chain (source says which). pending: true means no receipt yet, and fields the node did not report are null. Logs and decoded calls are not included.
| Name | Required | Description | Default |
|---|---|---|---|
| hash | Yes | ||
| chain | Yes | "bnb" = BNB Chain, "eth" = Ethereum |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, openWorld), yet the description adds real value: dual data provenance (explorer index vs on-chain, surfaced via `source`), pending-without-receipt semantics, and null-means-unreported. It omits error behavior (e.g., nonexistent hash) and any rate-limit/retry guidance, so not a 5.
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?
Three dense sentences, front-loaded with the core identity (one transaction by hash) followed by field list, then provenance/pending/null caveats. No filler and nothing repeated from annotations or schema.
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?
With no output schema, the description carries the return-value burden and does so — returned fields, `source`, `pending`, and null semantics are all covered. Missing only failure behaviour for an unknown hash, which is a minor gap for a two-param read tool.
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 description coverage is 50%: `chain` is documented in-schema via enum descriptions, `hash` is only constrained by a regex pattern. The description implies chain scope ('BNB Chain or Ethereum transaction by hash') and clarifies value units (wei), but adds little beyond what the schema already enforces, so baseline 3 is right.
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?
States a specific verb+resource (fetch one transaction by hash), the supported chains, and enumerates the returned fields. The sibling get_token is a different resource, and the description's scope ('transaction') makes the boundary obvious without needing to name it.
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?
Gives clear context for what the tool returns and explicitly declares a scope boundary ('Logs and decoded calls are not included'), which steers agents away from expecting receipts/logs. It never states when not to use it or names an alternative, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_tokenget_transactionSigned BNB Chain reads (balances, tokens, NFTs, prices, TapeOut names) with verifiable receipts
Read-only Etherscan V2 blockchain data: balances, transactions, transfers, tokens, contracts, logs.
Explore blockchain data across addresses, tokens, blocks, and transactions. Investigate any transa…
Blockchain data across 100+ chains: token prices, NFTs, transfers, simulation, traces, Solana DAS
Add one secure layer between your agents and this server.
