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

With no annotations, the description carries full behavioral burden and does disclose the x402 payment requirement and per-call price, which is valuable. However, it omits whether the nonce reflects pending or latest state when the mempool is busy, error behavior for malformed/unused addresses, and whether calls are rate-limited or cached.

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?

Three short sentences: what it returns, when to use it, and what it costs. The most decision-relevant fact (the returned resource) is front-loaded and nothing is redundant.

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?

For a simple 2-parameter read tool with no output schema, the description covers purpose, usage trigger, and the otherwise-hidden payment/cost model. The remaining gap — exact return semantics (pending vs latest nonce, failure cases) — is modest but real.

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 both parameters are already documented, making 3 the baseline. The description adds only marginal semantics — 'for any address' and 'on Base' hint that the chain parameter is effectively Base-only, but it does not explain the chain param's accepted values or defaults.

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 the exact resource returned — 'the next transaction nonce for any address' on Base — which goes beyond restating the name by specifying it is the pending/next nonce. The resource is naturally distinct from sibling tools like evm_balance or evm_tx, but no sibling is named, so this lands just short of a 5.

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 it to build a transaction without racing the mempool' gives a concrete when-to-use scenario that an agent can pattern-match on. It offers no when-not conditions or alternatives (e.g., use evm_tx_status to check confirmation instead), so it stays at 4.

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