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

Annotations only declare readOnlyHint and openWorldHint; the description adds the critical non-obvious trait that nothing is pushed and the first call returns NO events while establishing a cursor, plus cap semantics (50 default, 1000 max, more_available means poll again immediately). This is exactly the behavioral detail annotations cannot carry.

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?

Dense but every sentence carries load: purpose, polling model, cursor handoff, sibling contrast, filters, cadence, cap behavior. Purpose is front-loaded in the first clause with no padding.

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 fully covers the return contract: first call returns no events plus a cursor, expandResult enumerates what accumulated since, and more_available signals the cap was hit. An agent has everything needed to drive the poll loop correctly.

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 address, sender, eventType and maxLogs are already documented at the schema level. The description largely restates them, adding only the useful note that row and body keys match getLogs; baseline 3 is appropriate since the schema does the heavy lifting.

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 (follow Sui Move events by polling) and immediately contrasts with the sibling getLogs, which it explicitly says scans a named checkpoint range. An agent can distinguish the two without opening either 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 explicit when-to-use (continuous following with no gaps) and when-not-to-use (getLogs for a fixed range), plus a concrete polling cadence tied to Sui's ~4 checkpoints/second and a rule for reacting to more_available. Nothing about selection is left to inference.

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