Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (destructiveHint=true, openWorldHint=true), the description discloses the private token header requirement, the public-visibility top-up prerequisite and one-time browser warning, WebSocket support, idempotency per port, and that rotate invalidates old tokens while session tokens are shown once. These are exactly the operationally risky behaviours an agent needs before calling a destructive, open-world 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?

Front-loaded with the address format, then one clause per action, with no filler sentences. It is a single dense run-on paragraph with seven embedded actions, which hurts scanability but every clause 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?

For a 10-parameter, no-output-schema tool this covers the action set, token lifetimes, embedding restrictions and partial return semantics (list 'with a fresh token', session_list 'without tokens'). Gaps remain on the 'origins' parameter and on how a session token is subsequently used.

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 coverage is 50% and the description largely restates schema-documented fields (visibility default/semantics, expiresAt, ttlSeconds, embedOrigins). It does add the header name and urlWithToken alternative for private previews, but it leaves 'origins' (session_create) unexplained, which is one of the undocumented parameters.

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 opening line states a specific resource ('HTTPS addresses for ports inside a sandbox') and the per-action clauses make clear this tool manages preview exposure and browser sessions rather than listing ports. It never names the obvious siblings (runtime_ports, runtime_sandboxes_network) to distinguish scope, which keeps it from a 5.

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?

Each action carries its own reason for use – rotate 'as when a link leaked', delete to 'stop sharing the port', session_create for 'a web page's token for this sandbox's commands, files and previews'. What is missing is tool-level routing: nothing tells the agent when to reach for this tool instead of runtime_ports or runtime_sandboxes_network.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.