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

With no annotations, the description must carry the whole behavioural load, and it does disclose real value: the $0.005 x402 cost, the per-chain finality thresholds (Ethereum 64, Polygon 128, OP-stack 60), and the no-receipt-vs-failed distinction. It still omits the mechanics an agent needs to act — how x_payment must be supplied, whether the call is a pure read, and latency/retry behaviour — which is a meaningful gap for an unannotated paid endpoint.

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 paid cost and the core question, then returns, then the two anti-footgun caveats in ascending order of importance. Dense but every sentence carries information; only the rhetorical closing clauses could be trimmed.

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 compensates by enumerating the return fields (status, block, tip, confirmations, gas used, fee paid, log count), and it supplies the chain-specific finality thresholds an agent needs to interpret them. The remaining hole is the undocumented payment parameter and the lack of any sibling routing guidance.

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 67%: hash and chain are documented, but x_payment has no schema description. The description adds context useful for x_payment by stating the $0.005 x402 cost, but never explains what value the parameter should carry. The two documented parameters are handled entirely by the schema, so the net contribution is thin.

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?

Names a specific resource (a transaction, addressed by hash and chain) and a specific purpose: did it land, how deep, is it final. It goes beyond a bare restatement by framing the finality question. It does not, however, name or contrast with the obvious sibling chain_transaction_status, leaving the boundary between the two 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?

Gives clear context for use — checking whether a payment is settled — and warns that 'a success with two confirmations is not a settled payment' and that 'no receipt yet' must not be conflated with 'failed'. What is missing is a routing rule: nothing tells the agent when to pick this over chain_transaction_status or chain_transaction_explain.

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