Set network VPN site alert

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

With annotations only covering safety and openness hints, the description adds extensive behavioral detail: exact alert timing, the initial null-state observation, 404 and 503 failure modes, ownership/2FA enforcement, async pending semantics, polling via in_progress and reason_code, and a no-automatic-retry policy. This is far beyond what annotations provide and is internally consistent.

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 definition is front-loaded with the core action and then packs in essential operational warnings. It is long but nearly every sentence carries useful behavioral information; the dense middle section could be slightly better structured, but it is not padded.

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 complex, asynchronous mutation tool with no output schema, the description covers what an agent needs: effect, permissions, failure codes, ownership and 2FA constraints, async polling rules, reason-code interpretation, and retry guidance. It is complete enough to invoke and monitor the operation correctly.

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 67% and the description meaningfully explains the enabled boolean by describing what enabled=true does and that the first observation records a null state. It adds less per-parameter meaning for peer_id and gateway_id, which the schema already documents as owned-resource UUIDs.

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 states a specific verb and resource: switching the office-down e-mail alert for one connected location. It is clear what the tool does, but it does not explicitly differentiate itself from nearby siblings like set_network_vpn_site_options or set_vpn_server_access.

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 gives strong practical context: read capabilities and state first, obtain approval, and the exact permissions required (networking:read or networking:manage). It does not, however, name alternative tools or describe when a different alert or option tool would be more appropriate.

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