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

With no annotations, the description carries the full burden and does substantial work: it discloses the payment requirement ($0.005 USDC via x402), the fact that numbers are validated against decoded facts with a template fallback, automatic network inference, and a curated selector table for function names. The main gap is failure behavior – nothing is said about invalid hashes, unconfirmed/failed transactions, or unsupported chains.

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?

Front-loaded with the trigger sentence, then organized as Input / Output / Example / Price, with no filler prose. The trailing price fragment and the pseudo-query-string example are slightly compressed, but every element carries information an agent would otherwise have to guess.

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 and no annotations, the description steps up by enumerating the return payload (explanation plus facts fields) and the accuracy guarantee, which is exactly what is missing from structured data. Only error and unsupported-chain behavior are left undefined, a minor gap for a two-parameter 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 coverage is 100%, so the baseline is 3, and the description does add a little: it spells out the concrete network values (eip155:8453|solana) that the schema leaves unenumerated and shows an example invocation. That is marginal beyond the schema's own 'default: Base for 0x hashes, Solana otherwise' note, so it does not lift the score.

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 ('tell a user what a transaction did') and clarifies the output is a human-readable explanation rather than raw decoded data. Scope is further pinned by the enumerated facts it returns (ERC-20 transfers, approvals, inferred swap, Solana programs). It falls short of a 5 because it never names the obvious siblings (base_tx, sol_tx) that return the raw equivalent, leaving that disambiguation to inference.

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?

'Use when an agent must tell a user what a transaction did' gives a clear, actionable trigger condition, and the example call plus the network-inference note tell the agent it handles both chains without a second tool call. There are no explicit exclusions or named alternatives, so the agent is not told when base_tx or sol_tx would be the better pick.

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