get_wan

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description reinforces this with "read-only state." Beyond annotations, it discloses important behaviors: pagination via `cursor` and `limit` with server defaults, the rejection of `site` for `vpn_links`, and the semantic nuance that `object_id` must be the leg ID from a topology tool's basenet view, not the parent path ID. No contradiction with annotations.

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 long but well-organized, with a clear intro sentence and a structured Args block. Every sentence contributes useful information: operation semantics, parameter requirements, edge-case behaviors (e.g., vpn_links rejection of site), pagination rules, and defaults. The structure is front-loaded with the core purpose and efficiently categorizes operations by tenant-wide vs site-required, so the length is justified.

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 tool with 9 operations and 6 parameters, the description is remarkably complete. It covers all operation-specific constraints, explains when site/element/object_id are required or ignored, describes pagination and defaults, and references `get_topology` for additional context. Since an output schema exists, the description does not need to enumerate return values, and the presence of `next_cursor` in the description complements the output schema.

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 baseline is 3. The description's Args section largely mirrors the schema descriptions, with only marginal additions like the general rule "Operations needing a site or element accept names or IDs" and the explicit note about `object_id` being from basenet. These add slight value, but the schema already conveys the same parameter meanings, so the description does not meaningfully go beyond it.

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 opens with a specific verb and resource: "Inspect WAN, VPN, VRF, LAN, and IPsec read-only state through one semantic tool." This clearly states the tool's function and scope, and the detailed operation list (networks, vrfs, ipsec_profiles, interfaces, paths, vpn_links, lan_networks, vpn_leg_status/state) distinguishes it from sibling tools like get_routing or get_interfaces by covering a distinct WAN-focused domain.

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 provides extensive usage context, including which operations require `site` or `element`, that `vpn_links` cannot be narrowed by site, and that `vpn_leg_status`/`vpn_leg_state` require `object_id`. It also points users to `get_topology` for matching legs to sites. However, it does not explicitly contrast with alternative sibling tools (e.g., when to use get_wan vs get_interfaces), so it stops short of full when-to-use/when-not-to-use guidance.

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