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

Consistent with the annotations (readOnlyHint, openWorldHint) and adds useful behavior beyond them: the result contains a `summary`, per-chain details, an explorer link, plus a `display` markdown block with chan images that must be surfaced to the user. That last point is a genuinely important non-obvious behavior for an agent. It does not mention size limits, unsupported/pending txs, or error cases.

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?

Purpose is front-loaded in the first clause, which is good, but the run-on list of per-chain details and the repetition around offering a quote then offering a swap ('often cheaper') makes it denser than it needs to be. The playbook sentence is relevant but tacked on rather than structured.

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?

There is no output schema, so the description correctly compensates by describing returns (summary sentence, details, explorer link, display markdown). Combined with full parameter documentation and annotations, an agent has what it needs to call and surface results; only failure/edge-case behavior is unaddressed.

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 100%, and the schema already spells out the accepted hash formats and the full chainId integer/name mapping. The description adds no parameter-level meaning beyond that (e.g., what happens if chainId conflicts with the hash's actual chain). Baseline 3 is appropriate when the schema carries the load.

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 and resource ('Plain-English explanation of any transaction') and then enumerates exactly what is decoded per chain (EVM transfers/approvals/fees, Solana balance changes and programs, BTC inputs/outputs, Tron TRX/TRC-20). An agent can tell this is the human-readable decoding tool, but the description never names siblings like tx_status, verify_tx, or read_chain, which also concern transaction data.

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?

It gives real downstream guidance: if the tx was a swap or transfer, offer a SwapChan quote and then a swap via get_quote/swapUrl, and it points to swapchan_playbook for broader workflows. What's missing is exclusions — no statement of when to prefer tx_status or verify_tx instead, so the boundary with transaction-checking siblings is left implicit.

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