infomaniak_manage_mailbox_forwarding

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

The annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds valuable behavioral context by mentioning the forwarding-address collection endpoint and the two-phase confirmation for mutations, which goes beyond the annotations. This helps the agent understand that mutations require a confirmation token and are not immediate. It does not detail specific side effects of delete, but the annotations cover destructiveness.

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 two sentences long, front-loaded with the core purpose. Every word adds value, with no filler or repetition of schema details. It efficiently covers the main actions and a key implementation detail.

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?

Given the output schema exists, return values are covered. The tool has 6 parameters, an enum, and nested objects, making it moderately complex. The description provides the essential purpose, the actions, and the critical two-phase confirmation behavior. It could mention that confirmation_token is required for mutations, but the two-phase confirmation implies that. Overall, it is complete enough for an agent to understand the tool's scope and proceed, though some action-specific payload requirements are not described.

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 67%, with descriptions for mailbox_name, mail_hosting_id, and forwarding_address, but not for action, payload, or confirmation_token. The description mentions the action categories and two-phase confirmation, which indirectly relates to the action and confirmation_token parameters, but it does not fully compensate for the undocumented parameters, especially payload which is a raw object with no semantics. The schema enum for action is clear, but the description adds limited parameter meaning beyond what the schema provides.

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 specific actions (list, replace, add, delete) on the resource 'mailbox forwarding addresses', which distinguishes it from sibling tools like manage_mailbox_aliases or manage_mailbox_auto_reply. It uses a specific verb-resource combination that leaves no ambiguity about the tool's 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 gives clear context that this tool manages mailbox forwarding addresses and notes the two-phase confirmation for mutations. However, it does not explicitly state when to use this tool over alternatives or provide any exclusionary guidance. It implies usage for forwarding address management but lacks explicit when/when-not guidance.

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