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

Annotations only cover readOnlyHint/openWorldHint, but the description adds substantial behavior: Tier 2 output shape {contract,event,args}, raw fallback with _event_unknown, the tier_degraded warning, ascending chunking with cursor and range_fully_scanned/note, the more_available vs full_count distinction, and liability to tier 0 on unbounded ranges. This is far beyond what annotations provide.

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-loads purpose, then tiers, then chunking behavior, then Sui specifics. Dense and mostly information-bearing, though sentences are long and the Sui paragraph could be tightened; still no dead weight.

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?

No output schema exists, so the description carries the return-shape burden and does so thoroughly: log tuple structure, undecodable fallback, tier_degraded, cursor, note, more_available, full_count, plus Sui row fields (checkpoint/digest/index). An agent has what it needs to call and interpret results.

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 cross-parameter semantics the schema lacks: address as package[::module] on Sui, fromBlock required for Sui, topics refused on Sui, and maxLogs bounding upstream fetch as well as display. It meaningfully supplements the parameter docs.

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 and resource (retrieve event logs on one chain, filtered by address/topics/block range) and immediately distinguishes the two operational modes. An agent can tell this apart from getTransaction, getBlock, or rpcCall without opening the 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?

Explains the conditions that select chunked scanning versus a single unbounded eth_getLogs call, and details the Sui path (checkpoint range, required fromBlock, topics refused). It does not name an explicit alternative tool (e.g. rpcCall) for arbitrary getLogs use, so routing is inferable rather than spelled out.

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