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

With no annotations, the description must carry the safety/behavior burden. It discloses what each mode returns (EIP-55 checksum + validity, 4-byte selector + topic0, keccak256 hash) and implies a pure, side-effect-free utility. It stops short of detailing exact response shapes or invalid-input handling, but no annotation contradictions exist.

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?

One dense sentence with a colon-led list; every clause corresponds to a distinct operation and no filler. The structure front-loads the tool's domain and lets an agent quickly scan the supported modes.

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 four-mode utility with no output schema, the description covers each mode's input and output at a useful level. The main gap is that `to`/`from` are schema-optional but description implies both are required for convert; a short example or explicit requiredness note would remove ambiguity.

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?

Although schema descriptions cover all four parameters, they are generic ('address / value / signature / text'). The description adds op-specific meaning by mapping checksum to addresses, convert to value+from+to units, selector to function signatures, and keccak to text, which is exactly what an agent needs to populate parameters correctly.

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 resource ('EVM developer utilities') and breaks it into four concrete operations with explicit input/output semantics: checksum, convert, selector, keccak. This level of specificity separates it from sibling EVM tools like decode_calldata and verify_signature, which address different concerns.

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?

Each operation includes its intended input ('input=address', 'input=function signature'), making selection within the tool explicit. It doesn't explicitly rule out alternatives, but the operation-level context is clear enough for an agent to pick the right mode.

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