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

With empty annotations, the description carries the full disclosure burden and does well: it reveals the data is read via RPC with source attribution and that a fallback mechanism exists. This tells the agent important non-obvious behavior (source dependency, resilience) beyond what any structured field provides.

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?

A single front-loaded sentence with zero waste: verb and resource come first, with the attribution/fallback behavior appended compactly. Every word earns its place.

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 zero-parameter read with no output schema, the description covers purpose and behavioral notes (RPC source, fallback) sufficiently. Only the return format is unspecified, which is minor for such a simple tool.

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?

Zero parameters, so the rubric baseline is 4. There is nothing to describe; the RPC-source attribution detail adds relevant context about how the result is obtained even though no inputs exist.

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 ('Read') and resource ('current Base mainnet block number'), making the tool's job unambiguous. It is distinct from the sibling base_* tools which read different resources (transactions, balances, nonces), though it doesn't explicitly name those alternatives.

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 implied — it's a read of block number on Base mainnet — but there is no explicit when-to-use guidance or exclusion relative to sibling tools like base_transaction or base_nonce. For a zero-parameter singleton read, this is adequate but not explicit.

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