mailboxes.listList the tenant's active mailboxes (owner is derived from the API key). Optionally look up a single mailbox by exact address.
| Name | Required | Description | Default |
|---|---|---|---|
| address | No | Exact mailbox address to look up (e.g. user@minutemail.cc). Optional. |
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is well covered. The description adds meaningful context beyond these annotations by specifying that only 'active' mailboxes are included and that ownership is scoped to the API key holder.
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, with the primary listing behavior stated first and the optional lookup behavior second. There is no fluff, and every clause contributes actionable information.
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?
This is a low-complexity tool with one optional parameter, an output schema present, and annotations covering the safety profile. The description adequately covers scope, auth-implied ownership, active-mailbox filtering, and optional exact-address lookup, so an agent has enough context to invoke it correctly.
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% for the single optional 'address' parameter. The description adds marginal value by restating that the lookup uses the 'exact address', but it does not provide additional format, behavior, or edge-case details beyond the schema.
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 a specific action ('List'), the resource ('tenant's active mailboxes'), the scope ('owner is derived from the API key'), and the optional filtering behavior ('look up a single mailbox by exact address'). It distinguishes itself from sibling mailbox tools by emphasizing the tenant-wide listing scope and exact-address lookup, which is not ambiguous next to mailboxes.get.
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 clear context for when to use the tool: to enumerate active mailboxes or retrieve one by exact address. It does not explicitly mention alternatives or exclusions, but the optional-address behavior implicitly signals that this tool serves both listing and targeted lookup use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool is scoped to a specific resource and action, and the dot-separated prefixes keep domains, mailboxes, mails, attachments, identities, OAuth clients, and team entities clearly distinct. Even similar actions like archived.delete vs mailboxes.delete or attachments.add vs mails.inject are unambiguous from context.
All tools follow the same resource.action pattern with lowercase dot-separated names and consistent plural resource prefixes. Multiword actions like delete_bulk and rotate_secret are consistently snake_cased, so the convention is predictable across all 40 tools.
At 40 tools, the surface is quite large and exceeds the 25+ threshold where tool sets become heavy for an agent to navigate. The grouping is coherent, but this many discrete operations would have been easier to manage with fewer, more consolidated endpoints.
The API covers the main lifecycle operations for mailboxes, mails, attachments, archived items, domains, identities, OAuth clients, and team members, with no dead ends in core flows. Minor gaps exist, such as no domains.get, no team.invitations.get, and no mailbox update/expiry operation, but these are workable via list operations.