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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral context on top: the data source is the public explorer, zk-proof/batch-finalization data is absent (a data-coverage limitation an agent can't infer elsewhere), and calls cost $0.002 USDC via x402 on Base, Solana or Arc with failed calls uncharged — effectively the payment/authorization model. That is precisely the kind of information the annotations do not carry.

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?

Information is front-loaded: what data first, then the excluded data, then price last — the right order. The metric list is dense but every item is a distinct returnable field, so little could be cut; the one wasteful element is the redundant restatement of the 1-to-10 block bound already in the schema.

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 one-parameter read-only stats tool with an output schema, the description covers the gaps that matter: data source, metric inventory, explicit data exclusions, and the x402 payment/cost model. Nothing an agent needs in order to decide or pay for the call is missing.

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 single 'blocks' parameter already documents 'How many newest blocks, 1 to 10 (default 3)'. The description's 'newest blocks (1 to 10) with gas use and transaction counts' adds only the payload content of those blocks, not new syntax or constraints, so it sits just above the baseline for reinforcing the bound and default context.

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 description names a specific resource and scope: Scroll (zkEVM L2) network statistics from the public explorer, then enumerates exactly which metrics come back (total blocks/transactions, average block time, gas prices, utilization, today's transactions, newest blocks). Naming the chain separates it from the sibling L2 tools (crypto_arbiscan_l2_rollup, crypto_linea_consensys_rollup, crypto_optimism_superchain_tx) without needing schemas opened.

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?

Usage is clear from the scope statement: reach for this when you need Scroll L1-anchored L2 activity metrics from the public explorer. It also states the boundary condition (proof and batch-finalization status is not available here), which prevents a wrong call. It never routes to a named alternative, so it stops short of the top band.

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