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

Annotations already declare the safety profile (readOnlyHint=false, openWorld=true, idempotent=false, destructiveHint=false), and the description goes further: it explains the non-existent-block path (404, uncharged), states that failed calls are free, and explicitly reconciles the read-only anomaly (reads/computes only, but not marked read-only because each call is charged). This is exactly the 'why' that annotations cannot 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-loaded with verb+resource+return fields, then usage, then the edge case, then an example, then pricing. Every sentence carries a distinct fact (return set, alternative tool, failure semantics, cost model, read-only rationale) with no filler.

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 compensates by enumerating the returned fields. Combined with 404 behavior, pricing/charging semantics, and the read-only justification, an agent has everything needed to decide, call, and interpret this 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?

Schema coverage is 100% and the single parameter is fully documented, so the baseline is 3. The description adds a real semantic constraint the schema omits: the number is 'decimal' (not hex), and restates the default (latest when omitted), which is useful on an EVM block-number field where hex is a plausible alternative.

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 (Fetch) and resource (a block on Optimism), names the retrieval key (decimal number, or latest when omitted), and enumerates the returned fields (hash, timestamp, tx count, gas, base fee, producer). It also distinguishes itself from the adjacent fee tool by naming op_gas, so an agent can separate it from siblings like op_tx/op_receipt without opening a 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 an explicit use case (timestamps and confirmation counts) and an explicit alternative with its selecting condition (for current fees use op_gas). It also notes the omitted-argument default, so both the when-to-use and the how-to-call paths are covered.

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