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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the paid x402 model, the exact price ($0.0027 USDC per call), the failure behavior (returns payment requirements instead of a result), and the three ways to retry with payment. It also discloses trust boundaries — no chain verification or token identity check — which is critical for interpreting the decoded values correctly.

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 the core operation in the first sentence, then constraints, then payment mechanics — a sensible priority order with no filler. The payment sentence is dense but earns its place, as an agent must know about the 402 response to avoid treating it as an error.

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 2-parameter, no-output-schema tool, the description covers inputs, outputs (from, to, atomic value, optional decimal string), cost, and failure mode. The main omission is that it never states the response envelope or whether the raw atomic value is always returned alongside the formatted one.

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?

With 0% schema description coverage, the description carries the burden: it clarifies that 'log' is a Transfer log supplied by the caller (not fetched) and that 'decimals' is optional and, when given, converts the atomic value into a decimal string. It does not explain the fixed 3-topic structure or the decimals range/interaction with the returned value, so a small gap remains.

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 and resource: 'Decode one caller-supplied EVM ERC-20 Transfer log into from, to and exact atomic value.' It scopes the input (caller-supplied, single log) and names the exact outputs, so an agent can distinguish it from unrelated crypto siblings like ofac_crypto_screen or the broader data 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?

Explicitly excludes adjacent workflows ('No RPC, chain verification, token identity check or trading'), which tells the agent this is a pure offline parser and that no chain lookup happens. It also gives the exact retry procedure on payment failure. It does not name a specific alternative sibling for the cases it excludes, keeping it short of a 5.

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