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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses result limits (up to 100 logs, block lookback 1–1,000 default 50), the shape of returned fields (block, tx hash, topics), and pricing/billing behavior (per-call charge, first 25 free, failed calls free, repeats not free). The note that repeats are not free is precisely the kind of behavior an agent needs to avoid redundant calls, which the annotations alone could not convey.

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?

Purpose and method are front-loaded in the opening clause, with limits, returns, alternatives, pricing, and safety trailing in a logical order. It runs long, and folding the pricing and example into the same paragraph makes it denser than necessary, but no sentence is truly wasted information.

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 a three-parameter read-only tool with no output schema, the description covers inputs, return shape, caps, and cost, which is enough to call it correctly. The one minor gap is not saying what happens when a block window matches more than 100 logs (silent truncation vs. error), but the stated cap gives the agent enough to plan around it.

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 already carry descriptions, making the baseline 3. The description adds only marginal value — clarifying topic0 as a 32-byte event signature hash and providing a concrete address example — while the blocks range/default merely restates the schema.

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 a specific verb and resource ('Recent contract event logs on Arbitrum One'), ties it to the underlying RPC method (eth_getLogs), and states the scope (last N blocks, topic0 filter, up to 100 logs). It also distinguishes itself from the nearest sibling by pointing to arb_receipt for single-transaction outcomes, so an agent can separate it from arb_tx/arb_receipt without opening a 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 gives explicit usage context ('Use to watch transfers or contract events') plus an exclusion with a named alternative ('for one transaction's outcome use arb_receipt'). The only weakness is that 'watch transfers' could also route to arb_token_transfers, which is not acknowledged, leaving a small ambiguity in the guidance.

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