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

Beyond the readOnly/idempotent annotations, it discloses chunked window walking, response-size-related refusals, reporting ranges no node would serve instead of failing a settled call, per-call cost, and supported chains. This gives the agent a detailed expectation of execution behavior and error handling.

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?

Four dense sentences plus a concrete REST example with no filler. The core operation is front-loaded before cost, chains, and the example, and every sentence earns its place.

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?

Between the annotations, schema, output schema, and this description, an agent knows parameters, filters, block cap, chain support, cost, and failure behavior. The description does not need to explain return values because an output schema exists.

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 schema already documents all five parameters. The description adds value by clarifying the 1000-block cap, the address/topic filtering requirement, and the toBlock default behavior, which goes beyond baseline but stops short of per-parameter documentation.

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 opens with 'eth_getLogs over a bounded window (max 1000 blocks) with an address and/or first topic — transfers and events without running an indexer', giving a definite verb, resource, and access mechanism. This clearly separates it from sibling chain block/transaction tools, and the title reinforces the address/topic focus.

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 intended filter conditions (address and/or topic), the block-window constraint, supported chains, and warns that unfiltered scans are refused, so an agent knows when it fits a request. It does not explicitly name a sibling alternative, but the context is clear enough for bounded log queries.

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