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

Annotations only cover readOnly and openWorld; the description adds substantial behavior on top: selector-collision rejection via re-encoding, multicall batch expansion, and a specific warning taxonomy (unlimited approvals, approve-all-NFTs, permits, ownership changes, upgrades). It also discloses the paid-call model and price ($0.005 USDC on Base via x402), which is critical pre-invocation information an agent cannot get from structured fields.

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?

It is one dense sentence, but it is front-loaded with the action and ordered from core behavior to secondary warnings to price. Every clause carries information; the only minor cost is that the packed clause list slows scanning slightly.

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?

With no output schema, the description still conveys what comes back — decoded signature, argument values, expanded multicall calls, and warnings — and it discloses the paid x402 model and chain-agnostic scope. For a single-parameter, read-only decoding tool this covers everything an agent needs to decide and call correctly.

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?

There is a single required parameter with 100% schema description coverage that already states the hex format and 16 KB cap. The description adds no further parameter-level meaning, so the baseline 3 applies; no credit is warranted for restating what the schema covers.

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 a specific verb+resource+stage: 'Decode EVM transaction calldata before signing.' It enumerates the concrete capabilities (signature DB lookup with re-encoding verification, argument decoding, multicall expansion, risk warnings), which clearly separates it from sibling tools like evm_typed_data_check and base_tx.

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?

'before signing' states the decision context in which to reach for this tool, and 'Works for any EVM chain' tells the agent it does not need to route by network (unlike base_* siblings). It stops short of naming an explicit alternative or when-not-to-use case, so it falls one step 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.