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

Annotations already mark it read-only and non-destructive, and the description adds genuine value beyond them: HTTP 400/404 outcomes, that failed calls are uncharged, the per-call price with x402/card payment, the 25-call free tier, and the reason repeats are not free (which explains idempotentHint=false). This is exactly the disclosure annotations cannot carry.

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 core action and mechanism list, with usage and error semantics following efficiently. Minor waste: charging is mentioned twice ('both uncharged' for 404/400, then 'failed calls free'), and the payment details could be tightened without losing information.

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?

There is no output schema, and 'names the kind found' only gestures at the response contents (implementation address, proxy type) without stating its shape. Everything else an agent needs to call it correctly — eligibility, errors, cost — is present, so this is a small gap rather than a blocking one.

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 coverage is 100% for the single 'address' parameter, so baseline would be 3. The description goes further by giving a concrete valid address example and specifying the failure mode for a malformed address (400) versus an address with no code (404), which helps the agent supply a correct, well-formed value.

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 Celo') and enumerates the exact mechanisms read (EIP-1967 impl/beacon/admin, EIP-1822 UUPS, legacy OZ, EIP-1167 bytecode) plus the output ('names the kind found'). This is unambiguous against siblings like celo_storage or celo_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?

Explicitly states when to use it ('before trusting or decoding a contract whose code can be swapped by its admin') and names the alternative for the adjacent need ('for a fuller risk verdict use contract_risk'). The condition that selects each path is spelled out rather than inferred.

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