rotate_hmacPOST /auth/v1/agent/hmac/rotate. Previous HMAC dies immediately. Requires an existing callback_url (400 callback_url required before rotate otherwise). Pass callback_url here to PATCH webhook first. Plaintext HMAC is returned once — store it; never a Wallet JWT.
| Name | Required | Description | Default |
|---|---|---|---|
| No | |||
| callback_url | No | ||
| jwe_public_key | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal destructive and non-idempotent, but the description adds critical non-obvious behavior: the previous HMAC dies immediately, the plaintext HMAC is returned only once, and it is never a Wallet JWT. This is exactly the context an agent needs before invoking a destructive secret-rotation tool.
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 dense and front-loaded: endpoint, immediate consequence, prerequisite, failure mode, and one-time secret all fit in five short sentences. Minor redundancy and the slightly ambiguous 'here' keep it from a 5.
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?
Core behavior, prerequisite, failure mode, and secret return semantics are covered. However, two of three parameters are undocumented, there is no output format beyond 'plaintext HMAC returned once,' and the only error condition mentioned is the 400 for callback_url. For a mutation tool with no output schema and no parameter descriptions, this is incomplete.
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 0%, so the description must carry parameter meaning. It explains callback_url's role in the PATCH-before-rotate flow, but email and jwe_public_key are completely unexplained. The agent is left guessing what those optional parameters do, which is a substantial gap.
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 names the HTTP endpoint, the verb (POST), the resource (webhook HMAC), and the core effect: rotating the HMAC makes the previous one die immediately. This is clearly distinguishable from sibling tools like set_webhook and leaves no doubt about what the tool does.
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?
It states the prerequisite of an existing callback_url, the 400 failure if absent, and the ordering requirement to PATCH the webhook first. It does not explicitly name an alternative sibling tool, but the context of when rotation is allowed versus when a webhook must be patched first is clear.
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: card creation, card detail, top-up, eSIM/gift purchase, KYT initiation, KYT polling, and history are all separated. The KYT family is the main risk area, but the descriptions clearly distinguish check, get, checks, and quote.
The dominant pattern is verb_noun snake_case, e.g., list_cards, purchase_gift, topup_card, get_balance. The KYT group is inconsistent—kyt_check, kyt_check_get, kyt_checks, kyt_quote—and set_webhook/rotate_hmac break the pattern slightly, but the overall set remains predictable.
19 tools is above the typical 3-15 sweet spot, but the count is justified by the range of spend rails and supporting operations: cards, eSIM, gift cards, KYT screening, notifications, and webhook management. No tool feels truly redundant, though the KYT cluster adds some bulk.
Core purchase and card workflows are covered: create, topup, details, list, and buy operations exist for cards/eSIM/gifts, plus deposit and KYT screening. However, there is no transaction/spend history, no card freeze or block action, and no explicit purchase status/refund flow, which are notable gaps for a spend-focused server.