Enable capability-token protection on an owned link. Returns a share URL that carries the capability — anyone holding that URL can view the link. A viewer secret code is also set, but it is shown only in the serve console, never here.
| Name | Required | Description | Default |
|---|---|---|---|
| ttl | No | Optional TTL duration (e.g. 24h, 7d). | |
| label | No | Label of the link to protect (optional; defaults to first active link). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, the description adds meaningful behavioral detail: the returned URL carries the capability, anyone holding it can view the link, and a viewer secret code is set but only visible in the serve console, never returned here. It does not contradict the destructiveHint annotation, though it does not elaborate on what destructive side effects may occur.
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?
Three concise sentences, each serving a purpose: the action, the primary return value with an important security caveat, and the behavior of the secret code. No redundant or extraneous wording.
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?
With no output schema, the description adequately conveys the main return value and what is not returned. However, it omits details about the destructive nature hinted by the annotation, how the 'owned link' requirement is enforced, and how the viewer secret code can be retrieved in the serve console.
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%, so the schema already documents both ttl and label. The description itself adds no parameter-level meaning beyond implying the link must be owned and active for the label default behavior; it does not discuss TTL at all.
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 the action ('Enable capability-token protection') and the resource ('an owned link'), and it clarifies the return value (a capability-bearing share URL). It is distinguishable from siblings like unprotect_link or revoke_link by the 'protection' framing, though it does not explicitly name the alternatives.
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 implies this is used when a user owns a link and wants to enable capability-token protection, and it warns that anyone holding the returned URL can view the link. However, it never explicitly says when to choose this over unprotect_link or revoke_link, and no exclusions or prerequisites are articulated beyond 'owned link'.
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 lifecycle tools (serve, stop_remote, protect_link, renew_link, revoke_link, unprotect_link) are clearly distinct. The only ambiguity is between account_status and links, which both report usage, live tunnels, and owned-link counts, though one is an account-level summary and the other a detailed link listing.
Most tools follow a clear lowercase verb_noun pattern (protect_link, renew_link, revoke_link, unprotect_link, stop_remote). The main inconsistency is that query tools are nouns (account_status, links) and serve is a bare verb, but the style remains readable and predictable.
Eight tools is well-scoped for a serve-and-link-management server: one publish action, one unpublish action, four protection lifecycle operations, and two query/status tools. Each tool earns its place without bloat.
The set covers the full remote-link lifecycle: publish content, stop/unpublish it, list links, check account status, and protect/renew/revoke/unprotect access. No obvious dead ends or critical missing operations for the stated purpose.
