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

Goes well beyond the annotations: it discloses pricing ($0.003/call via x402 USDC or card key, first 25 free, failed calls free) and, crucially, explains WHY readOnlyHint is false ("not marked read-only because each call is charged"), reconciling a potentially confusing annotation. It also confirms the operation is compute-only with no destructive effect.

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?

Front-loaded with purpose, then usage, then a concrete example, then pricing and the annotation rationale. Dense but every sentence earns its place — nothing is redundant given the billing and read-only nuance it must convey.

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?

No output schema exists, and the description covers purpose, input forms, usage, cost, and safety. The one minor gap is that it never states the return format (e.g., 0x-prefixed 32-byte digest), which an agent would need for downstream chaining.

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 single parameter is already documented, but the description adds a concrete worked example (text=transfer(address,uint256)) that meaningfully clarifies the expected input format for a hashing tool beyond the schema's generic wording.

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 (Keccak-256 hash) plus the accepted input forms (text or 0x hex bytes) and the domain use (function selectors, event topics, storage slots). This cleanly distinguishes it from every sibling, which are all chain-specific RPC read tools.

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?

"Use when building or decoding EVM calls" gives clear context for when to reach for this tool. No alternatives or exclusions are named, but none are needed since no sibling performs hashing — the only omitted routing detail is trivially implied.

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