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

Annotations already cover readOnly/destructive/openWorld, but the description adds real value beyond them: a hard cap of up to 100 returned logs, the pricing model ($0.01/call, first 25 free, failed calls free), and the fact that repeats are not free — which concretely explains the idempotentHint=false. It does not explain truncation or ordering of results when more than 100 logs match.

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 functional content is front-loaded in the first two sentences, then the alternative routing, then pricing. It is somewhat padded — the pricing/credits sentences are long and 'reads or computes only and changes nothing' repeats readOnlyHint — but nothing is genuinely off-topic.

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 does its job by sketching the return shape (up to 100 logs with block, transaction hash and topics) and covering costs and the sibling alternative. The remaining gap is behavior when the result set exceeds 100 logs or how topics are ordered, which matters for a log-scanning 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%, so all three parameters are already documented. The description restates the blocks range (1-1,000, default 50) and clarifies topic0 as a 0x 32-byte event signature hash, but adds little beyond the schema text and supplies only an example address value rather than format guidance.

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 names the specific RPC method (eth_getLogs) and the resource (contract event logs on Scroll), and explicitly contrasts itself with the sibling scroll_receipt for single-transaction outcomes. An agent can distinguish it from scroll_token_transfers or scroll_receipt without opening any 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?

It states the use case ('watch transfers or contract events') and names the alternative tool with the condition that selects it ('for one transaction's outcome use scroll_receipt'). This is explicit when-to-use plus explicit alternative routing.

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