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

With no annotations, the description carries the full burden and does a decent job: it enumerates the returned fields (number/hash/parentHash/timestamp/gas/baseFee/tx count/miner), discloses the 502 failure mode when pending data is unavailable, and states the price ($0.001 USDC). It does not say whether a partial result is returned alongside the 502 or what the response envelope looks like.

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?

Everything is packed into a few front-loaded clauses with no filler; the field list, error mode, example, and price each contribute. The telegraphic style ('vs latest head age') is slightly terse at the cost of a quick read, but nothing is wasted.

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 tool with no output schema and no annotations, the description covers purpose, returned fields, failure mode, and cost, which is most of what an agent needs. The remaining gap is operational detail: supported chains, default behavior when chain is omitted, and what a successful response contains when pending is unavailable.

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 0% for the single 'chain' parameter, so the description must compensate, and it only partially does so via the example {chain:"base"}. It shows the value format but omits supported chain names, whether chain is required or defaults, and what happens with an unknown chain.

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 verb/resource pair ('pending + latest block snapshot') and the underlying method (eth_getBlockByNumber), so the agent knows exactly what data comes back. It implicitly separates itself from siblings like chain_block_number and block_lookup by framing the result as a pending-vs-latest comparison, but it never names those alternatives outright.

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 only implied: the pending-versus-latest-head framing suggests when to reach for it, and the note that public RPCs may omit pending gives one concrete failure condition (502). There is no explicit statement of when to prefer this over chain_block_number, block_lookup, or chain_network_info.

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