Get network VPN peer history

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

Beyond the readOnly/idempotent annotations, the description discloses retention windows per resolution, that unobserved periods yield no point rather than 0, the rx/tx byte direction, and protocol-specific liveness definitions (WireGuard 180 s handshake vs IPsec SA state, with the CHILD-SA rekey caveat). It also states auth requirements (networking:read / networking:manage, not covered by full/read defaults) and backend ownership, feature and 2FA enforcement.

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 verb and resource, then layered detail in descending importance; every clause carries information. The IPsec CHILD-SA rekey aside is the one clause that borders on over-detail for the space it occupies.

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?

No output schema exists, and the description compensates well by defining point ordering, resolutions, and the meaning of rx/tx and 'connected'. It never sketches the shape of the returned series (field names, unit of each point) or ordering guarantees across mixed resolutions, which is the remaining gap for a history-read tool.

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 two UUID params are self-documented, but the description carries real weight for `range`, explaining each enum value's sampling interval and source retention. It does not clarify how peer_id resolves when the peer is a site vs a device, leaving a small 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?

"Read one device's or site's traffic and connection history" states a specific verb (read), a scoped resource (one peer's history) and the unit of observation (device or site). It is clearly distinguishable from get_network_vpn_gateway, which the description explicitly names as the only place the endpoint IP lives.

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 gives concrete selection guidance for the range parameter (24h raw, 7d 10-minute, 30d hourly, 13m daily) so an agent can pick the right window, and it redirects the agent to get_network_vpn_gateway for endpoint IP. It stops short of explicitly contrasting with get_network_vpn_summary or stating prerequisites/order of calls.

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