upgrade_proxy

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

With no annotations provided, the description must convey behavioral traits. It only states the action without disclosing that this is a state-changing transaction requiring a private key, that it may have security implications, or that there are different proxy upgrade patterns (transparent vs UUPS) with specific behaviors. It also omits any post-upgrade call behavior or error conditions. The description is too shallow to prepare the agent for the tool's side effects.

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 description is a single, concise sentence that directly conveys the core action. It is appropriately sized and front-loaded, with no redundant or extraneous information. Every word earns its place.

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?

Proxy upgrades are complex operations involving multiple parameters (including private key, calldata, proxy type) and significant security considerations. With no output schema and no annotations, the description is far too sparse to be complete. It lacks context about preconditions, consequences, and recommended usage patterns. The agent would benefit from details about upgrade ownership, admin roles, and the significance of the upgrade process.

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 100%, so the schema already documents all eight parameters. The description adds no additional parameter detail beyond the schema. While it mentions the key addresses (proxy and new implementation), the schema provides the necessary semantics for proxyType, calldata, and admin address. This meets the baseline for high schema coverage.

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 description clearly states the tool's action: upgrading a proxy contract to a new implementation address. This is specific and distinct from sibling tools like deploy_proxy, which creates a new proxy, and write_contract, which is a generic contract call. The verb 'upgrade' and resource 'proxy contract' immediately convey the tool's purpose.

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 description offers no guidance on when to use this tool versus alternatives, nor does it mention prerequisites like ownership or proxy admin requirements. There is no indication of what situations warrant an upgrade (e.g., deploying a new implementation, managing transparent vs UUPS proxies) or when to prefer other tools like deploy_proxy or simulate_transaction. The context is purely definitional.

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