Remove an SSH key from your account. This does not affect servers already built with it, and the key can simply be added again. Requires authentication. Required: keyId (integer key id from listMySshKeys).
| Name | Required | Description | Default |
|---|---|---|---|
| keyId | Yes | ||
| 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. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the non-destructive effect on existing servers, the reversibility of adding the key again, and the authentication requirement. This goes beyond a bare 'delete' statement and helps an agent anticipate consequences.
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 compact and front-loaded: the action is stated first, followed by the most decision-relevant caveats. Every sentence contributes either operational guidance or behavioral context, with no filler.
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 two-parameter delete operation with no annotations and no output schema, the description adequately covers purpose, side effects, reversibility, authentication, and parameter sourcing. It doesn't describe return values or error behavior, but those are less critical for this simple call.
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 adds real value for the required keyId parameter by specifying it is an integer and directing the agent to listMySshKeys as the source. The sessionKey parameter is already documented in the schema, so the 50% schema coverage is compensated where it matters most.
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 a specific verb and resource: 'Remove an SSH key from your account.' This clearly distinguishes it from sibling tools like addSshKey and listMySshKeys, and explicitly says the deletion is scoped to the account.
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: the key is removed from the account but not from already-built servers, and it can be re-added later. It doesn't explicitly name alternatives like addSshKey, but the behavioral context is enough for an agent to infer the appropriate use case versus other SSH-key tools.
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.
The set has several near-duplicate or heavily overlapping tools: initiateTransfer and transferDomain appear to do the same thing, and generateDomainSuggestions, bulkDomainSuggestions, suggestAlternatives, spinDomainWords, and addPrefix/addSuffixToDomain all occupy suggestion space. Account/profile tools like getAccountSummary, getMyProfile, getRecentActivity, and getMyAuditLogs also blur together.
Many tools follow verb_noun camelCase (createDnsRecord, listInvoices, updateContact), but the broader set mixes styles: osirAppCreateUpload vs osirAppList vs osirAppStatus, plus inconsistent verbs like check/verify/validate/preview for similar lookup actions. The naming is readable but not predictable across the full surface.
105 tools is an extreme count for any single MCP server, even one spanning domain registration, DNS, VPS, email, billing, app deployment, and site publishing. The surface would be far more coherent split into focused servers by domain.
Core domain, DNS, billing, VPS, mail, and app deployment workflows are broadly covered. However, there are notable gaps: no way to update or reassign the contacts on an existing domain, no update operation for host/glue records, and no VPS power operations like reboot or stop outside the external control panel.