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

No annotations are provided, so the description carries full burden. It reveals that the tool returns calldata rather than executing a deployment, defaults to B20 with immediate activation, and atomically grants MINT_ROLE to the merchant admin and the agent's wallet (or explicit extra_minters). These are critical behavioral traits that an agent needs to know before invoking the tool, and they go well beyond what the schema states.

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 three sentences, front-loaded with the core purpose. The second sentence explains the default and alternative, and the third sentence conveys an important side-effect. Every sentence earns its place, with no redundant or filler content.

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 an 11-parameter tool with no output schema and no annotations, the description covers the core deployment workflow, the B20 vs erc20 choice, and a critical mint role behavior. Still, it omits explicit guidance on what to do with the returned calldata (e.g., send as a transaction) and does not mention the erc20 follow-up in the description itself, although the schema does. The undocumented locale/preferred_style/target_audience parameters also remain unaddressed.

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?

The description enriches meaning for key parameters: token_standard (default vs legacy), extra_minters/agent_wallet_address (MINT_ROLE atomic granting), and implies the need for name/symbol. Schema coverage is 73%, leaving locale, preferred_style, and target_audience undocumented in both schema and description. However, the description still adds substantial value beyond the schema for the most operationally important parameters.

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 opens with 'Get factory calldata to deploy a new loyalty token on Base,' providing a specific verb, resource, and platform. It clearly distinguishes from sibling tools like create_reward or create_gift_certificate by focusing on deploying a token rather than creating rewards or certificates, and it differentiates from activate_loyalty_program as a deployment-time action.

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 explicitly states the default token_standard ('b20') and how to switch to the legacy factory via 'token_standard='erc20''. It also explains the benefit of B20's atomic MINT_ROLE granting, which helps the agent decide when to use B20. However, it does not explicitly direct users to alternative tools like activate_loyalty_program for the erc20 follow-up, so exclusions are only implicit.

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