reissue_keyMint a new account nv_ key from email OTP. No Bearer key required. WARNING: revokes prior account-scoped nv_ keys. Also verifies email if needed.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | ||
| Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the destructiveHint annotation, the description explicitly warns that prior account-scoped nv_ keys are revoked and that email verification may occur as a side effect. It also states the auth requirement, adding substantial behavioral context over the annotation alone.
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, front-loads the core purpose, and each clause adds useful information: no Bearer requirement, revocation warning, and optional verification. There is 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?
The description covers purpose, side effects, and auth, but with no output schema it does not mention what the tool returns or how the OTP is acquired. For a key-issuing tool, specifying that it returns the new key would be an important missing detail.
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?
With zero schema description coverage, the description compensates by identifying `code` as an email OTP and tying it to `email`. It does not detail expiration or format, but the essential meaning of both parameters is conveyed.
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 action, 'Mint a new account nv_ key from email OTP,' which names the resource, the source of authorization, and the authentication mechanism. It also notes that no Bearer key is required, separating it from bearer-authenticated account tools.
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: use this when you have an email OTP and need a new account nv_ key without a Bearer key. It does not explicitly name alternative tools or exclusions, but the stated conditions are concrete enough for an agent to choose it.
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 map to a clear resource+action pair, and the descriptions explicitly separate similar sounds like checkout vs mpp_upgrade and get_upload_url vs get_upload_urls_batch. A few tools overlap in reported data (get_account, get_quotas_and_usage, get_project_usage), but their descriptions make the scoping clear enough for selection.
The set overwhelmingly follows a consistent snake_case verb_noun pattern: list_projects, create_project, update_project_settings, delete_form_submission. A few names like billing_portal, checkout, bootstrap, and mpp_upgrade deviate from that pattern, but they are still short and readable.
43 tools is a large surface, and many are micro-endpoints such as get_upload_url/get_upload_urls_batch, confirm_upload/confirm_uploads_batch, and several overlapping usage/account views. The broad platform scope explains some of the size, but the collection feels over-fragmented and heavier than an agent needs.
The server covers core lifecycle workflows for projects, files, deploys, billing, members, and forms. Notable gaps remain: there is no delete_project, delete_form, or remove/delete custom domain, so the surface is not fully CRUD-complete for the domain it represents.