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

Annotations already cover readOnly/idempotent/non-destructive/closed-world, and the description adds real behavior beyond them: strict refusal of non-canonical encodings, recognition of reverts and panics, and the fact that computation is pure and local. It doesn't describe output shape per op in exhaustive detail, but that is minor given the annotation coverage.

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 op enumeration and scoped tight to a single dense paragraph where each clause maps to a real capability. The trailing playbook sentence with a seven-item workflow list is the one part that reads as promotional padding.

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 7-parameter tool with no output schema, the description still tells the agent what each op produces (selector + calldata, named args, functions/events/errors with selectors, ERC detection). What an agent needs to invoke it correctly is essentially present.

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 only 14% schema coverage, the description must carry the load and largely does: it explains sig as a canonical signature, args as a JSON list, input as hex, types for tuple return decoding, output=true for return-data mode, and abi as JSON or newline-separated signatures. Only the interplay/limits of abi vs sig in each op remain slightly implicit.

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 concrete verb+resource ('Solidity ABI work on public data') and immediately enumerates the three operations with their inputs and outputs, so an agent can tell it apart from bytecode_inspect, hash_tool, or typed_data_verify without opening the schema.

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?

Clearly frames the scope: pure offline computation, nothing fetched or stored, and explicitly routes workflow-level questions to swapchan_playbook with named workflows. It does not state when to prefer this over adjacent dev tools (bytecode_inspect, contract_reader), so it stops short of full when/when-not guidance.

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