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

Annotations already declare readOnlyHint/openWorldHint, so the safety profile is covered. The description adds real behavioral context beyond that: Tier 2 drops verbose header roots and bloom, includeTxs ABI-decodes and compacts transactions, and a large includeTxs payload can blow the compression budget (watch tier_degraded). These are meaningful operational caveats.

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?

The purpose is front-loaded and the sentence count is low, but it leans on undefined jargon ('Tier 2', 'tier_degraded', 'verbose header roots and bloom') that an agent cannot resolve from the definition itself, costing clarity per word.

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?

With no output schema the description must carry return-shape burden; it gestures at tiering and degraded mode but never explains the response structure or where tier_degraded lives. It is adequate for a read tool with full param coverage, but the unexplained tier machinery leaves an agent unsure how to act on the caveat.

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%, so the baseline is 3, but the description adds value the schema lacks by enumerating the actual tag values (latest, finalized, safe, earliest, pending) and by clarifying the Sui meaning of 'block' as a checkpoint number or digest. That goes beyond the schema's generic 'a tag' wording.

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 opens with a specific verb+resource ('Get a block') and enumerates the accepted identifiers (hash, number decimal/0x-hex, tags latest/finalized/safe/earliest/pending), which cleanly separates it from getTransaction and rpcCall. It is clear and self-contained, though it does not explicitly name a sibling it is not.

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?

There is implicit when-to-use guidance: use the tag forms for canonical blocks, use Sui's checkpoint semantics for that chain, and check tier_degraded when a block with includeTxs is large. But it never states when to prefer this over rpcCall or getTransaction, so usage is inferred rather than directed.

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