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

Annotations already establish readOnly/idempotent/closed-world, so credit here goes to the added facts: the computation is pure and offline ("nothing is fetched or stored") and the return value is an EIP-55 checksummed address, which no annotation or output schema conveys. Minor gap: no mention of what is returned when parameters are insufficient or conflicting.

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 core sentence is front-loaded and dense with real information; every clause about CREATE/CREATE2/EIP-55 earns its place. The final sentence enumerating unrelated playbook workflows (best-swap, rebalance, bridge-stuck) is tangential padding for an offline address-prediction 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 5-parameter, 0%-covered, no-output-schema tool, the description covers the two derivation modes, the return format, and the side-effect profile – enough to call it correctly. The remaining hole is edge-case behavior around init_code vs init_code_hash and nonce/salt precedence.

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, and it does: it maps deployer/nonce to CREATE and deployer/salt/init_code or init_code_hash to CREATE2, and notes the salt is 32 bytes. It does not explain the nonce's integer-vs-string form or the relationship between init_code and init_code_hash (both supplied? hash preferred?).

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?

"Predict a contract's deployment address" states a specific verb and resource, and the first sentence immediately splits the two supported modes (CREATE vs CREATE2/EIP-1014). An agent can distinguish this from sibling utilities like address_tool or hash_tool 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?

It gives good guidance on how to invoke each mode (deployer+nonce for CREATE, deployer+salt+init_code/hash for CREATE2), but says nothing about when to prefer this over alternatives such as address_tool, or what happens if both nonce and salt are supplied. The trailing swapchan_playbook sentence is a generic cross-sell listing unrelated workflows rather than a real routing rule.

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