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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds meaningful behavior beyond them: it explains why a failure occurred, refuses sensitive inputs (keys/seed phrases), and warns about address poisoning as a limitation rather than overselling a pass.

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 purpose sentence is dense and front-loaded, which is good, but the tail of the description is generic meta-instruction noise ('Put tool fields inside inputs', 'Follow its required fields and exact choices', 'Do not pass the REST calculator field inside MCP arguments') that says nothing about this specific tool and dilutes the useful content.

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?

An output schema exists, so return values need not be explained, and the read-only annotations remove safety questions. However, a validation tool with an 'auto' chain value should say that chain detection is supported, and nothing explains the accepted behavior for an ambiguous or multi-chain address — a notable omission for this tool's core job.

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 0%, so the description must carry the load. It compensates partially by naming which encodings the address may take (Base58Check P2PKH/P2SH, Bech32/Bech32m, EIP-55) and by naming five of the chain enum values, but it never mentions the 'auto' chain option, the 120-character address limit, or what modelVersion means beyond a generic 'supply it only when listed' line.

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 first sentence names a specific verb (check the FORMAT of) and resource (address) and enumerates the supported chains and encodings, so the tool is clearly distinguishable from the chain_* calculators that share the prefix. It falls short of a 5 only because it never states its relationship to any sibling tool.

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?

It explicitly bounds usage: format validation only, not proof of control ('beware address poisoning'), and it refuses private keys and seed phrases. That is a real when-to-use/when-not-to-use contract; the only gap is that no alternative tool is named for the ownership/balance questions the user might actually have wanted.

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