create_wallet

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

No annotations are provided, so the description carries the full burden and does so: key stored 0600 in the network's config section, session-scoped, only the address returned, never the key. It also discloses the destructive overwrite behavior and that the replaced key is unrecoverable.

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-loads what the tool does and the scope restriction before the operational details. It is dense and one sentence ('so create_wallet, login, create_api_key gets an agent an account...') is grammatically tangled, but nearly every clause conveys a constraint an agent needs.

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 single-optional-parameter tool with no output schema, the description covers prerequisites, return value (address only), persistence, environment limits, and refusal conditions. Nothing essential to correct invocation is missing.

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% and the confirm property is already documented as required-to-replace. The description nonetheless adds value by specifying that confirm overwrites the old key and keeps it nowhere, reinforcing irreversibility beyond the schema's terse wording.

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?

Specific verb+resource ('Make a new EVM wallet for this server to sign with') plus an explicit scope restriction (play-funds targets only). It is clearly distinguishable from sibling auth tools like login or register_agent, which it positions as consumers of the wallet rather than creators.

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?

Explicit when-to-use (play-funds targets only), when-not-to-use (refused on mainnet or undeclared/real funds), overwrite precondition (confirm: true required if a wallet exists), and environment constraint (stdio server only). It also names the downstream flow (login, register_agent, register_bridge_wallet, create_api_key) that becomes usable afterward.

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