setMailboxPassword: Set a new password on a mailbox. Never log or store the password. Requires authentication.
| Name | Required | Description | Default |
|---|---|---|---|
| password | Yes | The new mailbox password; never log or store it. | |
| mailboxId | Yes | Mailbox id from listMailboxes. | |
| sessionKey | No | Session key (osk_...) returned by checkDeviceLoginStatus. Pass it on every call when logged in via the in-chat device flow; omit when connected via OAuth. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / mailboxId / descriptionAdded value: +"Mailbox id from listMailboxes."Input schema / properties / password / descriptionAdded value: +"The new mailbox password; never log or store it."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds a meaningful security warning not present in the annotations: 'Never log or store the password.' It also notes authentication is required. Annotations already cover mutability and idempotency, so the description adds useful behavioral context beyond them.
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 short sentences, front-loading the action and then adding the critical security constraint. There is no filler; every sentence earns its place.
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 full schema parameter descriptions and annotations, the description supplies the essential behavioral caveats: authentication and password handling. It does not describe return values or side effects, but those are less critical for a straightforward mutation tool.
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%, with each parameter explained, including the conditional sessionKey. The description mostly restates the password warning already in the schema, so it adds little new semantic value, but the schema carries the burden adequately.
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 explicitly states the verb 'Set' and the resource 'a new password on a mailbox', making the action unambiguous. It is clearly distinct from sibling tools like createMailbox, deleteMailbox, or listMailboxes.
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 purpose is direct enough that when to use it is clear: reset or change a mailbox password. It adds the 'Requires authentication' context, and the sessionKey parameter documentation in the schema provides explicit guidance on when to include it, though the description itself does not name alternatives or exclusions.
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.
Most tools target distinct resource-action pairs, but there are several overlapping clusters: six domain-suggestion tools (addPrefixToDomain, addSuffixToDomain, generateDomainSuggestions, bulkDomainSuggestions, spinDomainWords, suggestAlternatives) and overlapping account-info tools (getMyProfile, getAccountSummary, getRecentActivity, getMyAuditLogs). Descriptions help, but with 105 tools an agent will regularly face near-identical choices.
The dominant convention is verbNoun camelCase (createContact, listDnsRecords, updateNameservers), which is readable and predictable. Deviations exist in the osirApp* and osirSite* families, where the noun precedes the verb, and a few names like suggestAlternatives and spinDomainWords break the pattern.
105 tools is far beyond a coherent MCP server surface; even if the platform genuinely spans domains, DNS, email, VPS, billing, and app hosting, this should be split into focused servers. Many tools are single-purpose getters that add selection overhead rather than earning their place as one integrated set.
The covered services have broad CRUD/lifecycle coverage: contacts, DNS, hosts, domains, email, VPS, SSH keys, invoices, and Osir apps all have create/read/update/delete paths. Some registrar-specific operations (e.g., contact reassignment after registration, domain deletion/redemption) are missing, and the sheer sprawl makes coverage hard to verify.