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

Annotations already cover the read-only/non-destructive profile, but the description adds substantial context beyond them: stateful baseline/cursor behavior, a hard cap of 10 extra tokens with USDC always included, and — most importantly — that the call costs $0.003 USDC via x402 with payment handled inside the MCP call, plus a free sample path. Payment/auth requirements and statefulness are exactly the traits annotations can't express.

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-loads purpose, then use cases, chains, params, pricing, and a copy-paste sample input — a sensible order. It is on the dense side and the param enumeration partially restates the schema, but every block carries actionable information, so it stays efficient.

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 carries the return burden — and it does, naming balance deltas, outgoing-tx count, and the cursor. Combined with pricing, payment method, chains, and a sample invocation, an agent has everything needed to call this correctly on first attempt.

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 80%, so the baseline is 3, but the description adds meaning the schema lacks: USDC is always included regardless of the tokens list, min_change_pct suppresses smaller balance moves, and the cursor must come from a prior call. Chain default and the supported chain list are also spelled out.

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 — 'watch an EVM address and get only what changed since your last call' — with the delta semantics plus outgoing-tx count. This clearly separates it from snapshot siblings like evm_balance, wallet_portfolio, and erc20_transfers, which an agent can tell apart without opening either schema.

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 concrete contexts: treasury and payment tracking, whale and smart-money watching, deposit detection. It also explains the stateful flow (first call saves a baseline, pass the cursor next time). No explicit when-not or named alternative tool, so it stops short of a 5.

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