Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes beyond the annotations, explaining that the tool fetches the transaction and receipt from the chain, decodes ERC-20 Transfer events using on-chain symbols/decimals, and prices fees. It also discloses the per-call cost. This is meaningful behavioral context not available from the readOnlyHint/idempotentHint annotations alone. It doesn't cover edge cases like failure modes, but the core behavior is well disclosed.

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 compact and efficiently structured: it opens with the primary output summary, follows with the underlying mechanics, and closes with pricing. Every sentence adds useful information, and there is no filler or repetition of the tool title. The content is front-loaded so an agent can quickly determine what the tool returns.

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 tool with only two parameters, robust annotations, and no output schema, this description is complete. It states the output contents, the chain-fetching behavior, ERC-20 decoding, fee pricing, and cost. An agent has enough context to select and invoke the tool correctly without additional documentation.

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 describes the chain parameter with an enum and default, and the hash parameter has a strict pattern. The description adds little direct parameter-level explanation: it implies the transaction is identified by hash but never names the parameter. With schema coverage at 50%, this is acceptable for two simple parameters, but the description does not substantially compensate for the undocumented hash parameter beyond the pattern.

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 states a specific verb and resource: it explains an EVM transaction, listing clearly what the output contains (status, from/to, value, fees in native/USD, method, and decoded ERC-20 transfers). This gives an agent a precise idea of what the tool does without needing to inspect sibling tools. While it does not explicitly name a sibling such as tx_explain, the detailed scope makes the tool's purpose unambiguous.

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 gives clear context for when to use the tool: for any EVM transaction that needs plain-language explanation and decoded ERC-20 transfers. It lacks explicit exclusions or named alternatives, but the phrase 'Any EVM transaction' combined with the detailed return content effectively establishes the intended use case. The cost disclosure also helps the agent decide whether to invoke it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.