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

Annotations only declare readOnlyHint and openWorldHint; the description goes well beyond by disclosing latency (20-60 s), async=true semantics, the x402 $2 USDC charge, and the no-charge-if-too-few-sources guarantee including the async pre-check nuance. It also states the output includes a model-written risk score, profile classification, red flags, next steps, and a PDF.

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 purpose and pre-transaction use case are front-loaded, and every sentence carries information (capabilities, output, latency, billing). The capability list is dense and slightly catalog-like, but nothing is padding.

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 fully carries the burden: it itemizes what the report contains, who writes it, the deliverables (score, profile, red flags, next steps, PDF), latency, async mechanics, and cost/failure billing. An agent has everything needed to decide and call correctly.

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%, so the baseline is 3, but the description adds real meaning on top: it explains that async=true returns a job id with the core source verified before queueing and charging, and that a PDF is included by default. It does not clarify webhook_url behavior beyond what the schema already says.

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 opening phrase names a specific verb+resource ('Wallet due-diligence report') and immediately enumerates the concrete contents (portfolio, Base/Ethereum balances, wallet-vs-contract classification, OFAC screening, agent-trust score, x402 history, NFTs, Hyperliquid exposure). This distinguishes it clearly from siblings like wallet_portfolio, wallet_nfts, sanctions, or token_report, which cover only fragments of the same surface.

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?

"before you transact" gives a clear triggering context and the description adds cost ($2 USDC via x402), latency (20-60 s), and the async option with its billing caveat. However, it never names an alternative for cheaper/faster needs (e.g., wallet_portfolio or sanctions) or states when NOT to use this expensive full report, so routing still requires inference.

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