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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so 'Read-only; builds no transactions' largely repeats structured data. The one genuinely additive behavioral trait is that the optional signature adds or validates the 4-byte selector, and that encoding is exact; nothing is said about failure behavior on decode or type mismatch.

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?

The opening two sentences are well front-loaded and dense with useful specifics. The remaining sentences are boilerplate that mentions an inapplicable 'units' field and an unexplained 'REST calculator field', which adds noise without adding meaning for this specific tool.

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 tool with a nested two-parameter schema and an output schema (so return values need no explanation), the description covers purpose, supported types, the signature fast-path, and read-only scope. The main remaining gap, which fields each mode requires, is arguably recoverable from the schema's required list and enum.

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 description coverage is low (0% per signals), so the description should carry more weight than it does. It clarifies that the optional signature adds/validates the selector and that tool fields belong inside the nested 'inputs' object, but it never explains the encode-vs-decode parameter pairing (types+values vs. data+types) and it references a 'units' field that does not exist in this tool's schema.

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?

Names a specific verb pair and resource ('ABI-encode or decode static values') and enumerates the supported type families (uint8..256, int8..256, address, bool, bytes1..32), which is far more specific than the title 'abi codec'. It stops short of explicitly distinguishing itself from the sibling buscalc_chain_abi_selector, despite both touching the 4-byte selector.

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?

The first two sentences imply usage (encode vs decode, optional signature for selector handling), and the mode enum reinforces it. But most of the tail ('Put tool fields inside inputs', 'Supply units or modelVersion only when listed in inputSchema', 'Do not pass the REST calculator field') is invocation hygiene rather than guidance on when to pick this tool over a sibling.

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