Event logs

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

Goes well past the readOnlyHint/openWorldHint annotations, disclosing tier degradation, chunked-scan semantics, cursor emission, and the exact flags that signal partial coverage (range_fully_scanned, more_available, full_count, note). It also warns about the undecodable-log fallback shape. This is exactly the behavioral context 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 front-loaded and organized: general semantics first, then the chunking/cursor contract, then Sui-specific rules. Every sentence carries load, though the prose is thick enough that some trimming is possible without information loss.

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 an 8-parameter, no-output-schema tool with subtle partial-result semantics, the description supplies the missing return-field contract and the conditions under which scanning is incomplete. Nothing an agent needs to invoke it correctly and interpret results is absent.

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 description coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: toBlock may be omitted and defaults to latest, fromBlock is mandatory for Sui, address is interpreted as package[::module] on Sui, and topics is rejected there rather than silently ignored.

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+resource: event logs on one chain, filtered by address/topics over a block range, and additionally covers the Sui variant (Move events over a checkpoint range). An agent can distinguish this from query siblings like getBlock or getTransaction immediately.

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 clear conditional guidance: concrete numeric bounds trigger ascending chunked scanning, any other bound collapses to a single unbounded eth_getLogs; on Sui fromBlock is required and topics is refused rather than ignored. It does not name alternative tools (e.g. suiWatchEvents for subscriptions), so it stops short of explicit alternatives.

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