Create Rappi address

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description correctly implies a write operation. It adds the behavioral requirement for explicit_user_intent, which is not fully captured by the annotations alone (though the parameter exists). It does not mention idempotency (annotations say false) or what happens on success/failure, but the description is consistent and adds some useful context.

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 extremely concise: two short sentences that front-load the primary action and then add critical caveats. There is no redundant phrasing or fluff. Every word contributes to clarity, making it easy for an agent to parse quickly.

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 write operation with 10 parameters and no output schema, the description is incomplete. It does not explain the required inputs (latitude, longitude, address) or how the saved address will be used (e.g., as a delivery location for future orders). It also lacks information about return values or side effects beyond saving. While it correctly notes that it does not place an order, an agent still lacks enough context to confidently invoke the tool with valid parameter values.

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 only 10%, with just explicit_user_intent explained. The description does not clarify the meaning of latitude, longitude, address, or any optional fields like tag, city, number, etc. It simply says 'delivery address', which is vague. With 10 parameters and minimal schema help, the description fails to compensate, leaving agents uncertain about what each parameter represents and how they combine.

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 verb 'save' and the resource 'delivery address', which is specific and aligns with the tool's name. It also adds 'Does not place an order' to distinguish it from order-related tools, but it does not explicitly differentiate from address update or delete operations, which are siblings. The purpose is clear enough for an agent to understand the core function.

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 provides a usage condition: 'Requires explicit_user_intent', indicating it should only be used when the user explicitly requests an address save. It also clarifies a non-goal: 'Does not place an order', preventing misuse. However, it does not mention when to use this over rappi_update_address or rappi_delete_address, leaving the agent to infer from the name. This is partial but not comprehensive guidance.

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