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

Annotations already declare readOnly/openWorld/non-destructive/non-idempotent, so the safety profile is covered. The description usefully adds error semantics (400 malformed, 404 no code, both uncharged) and the billing model (per-call charge, 25 free calls, failed calls free), which meaningfully explains the non-idempotent hint. It does not describe the shape of the returned result (detected kind, addresses) beyond mentioning it 'names the kind found'.

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?

Detection scope is front-loaded, then usage, then error/pricing behavior. Dense and mostly earned, though the pricing/credits sentence is long and could be trimmed without losing the decision-relevant point that repeats cost money.

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?

No output schema exists, but the description covers what is inspected, what is returned at a high level ('names the kind found'), failure modes with status codes, and cost. A brief note on what a non-proxy address returns would close the remaining gap.

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?

Only one parameter with 100% schema coverage, so the schema already carries the burden and the baseline is 3. The description adds a concrete example address, which pins down the expected 0x-prefixed format beyond the schema's terse '0x contract address'.

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 specific verb and resource ('Find the implementation behind a proxy contract on zkSync Era') and enumerates exactly which storage slots/standards it detects (EIP-1967 impl/beacon/admin, EIP-1822 UUPS, legacy OZ layout, EIP-1167 bytecode). This clearly distinguishes it from sibling proxy tools for other chains and from generic read tools like zksync_storage or zksync_call.

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?

Gives an explicit trigger ('Use before trusting or decoding a contract whose code can be swapped by its admin') and names the alternative for a different need ('for a fuller risk verdict use contract_risk'). The agent knows both when to pick this tool and when to route elsewhere.

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