update_network

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

Annotations only mark destructiveHint=true, so the description carries the burden of explaining the mutation. It adds that changes are applied immediately and persisted, that a single field change preserves other settings, that confirm=true is required, and that VLAN/routing/enable-state changes can disconnect clients. It also documents the special DHCP-disable behavior, which is valuable beyond the annotation.

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 front-loads the most important behavioral facts: patch semantics, mutating operation, immediate persistence, and safety gate. The Args section is structured and gives one-line explanations per parameter, though it duplicates much of the input schema. There is no fluff, but the redundant parameter list keeps it from being a 5.

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?

Covers the target resource, patch semantics, persistence, confirm requirement, client-disconnect risk, the DHCP special case, and points to get_networks for verification. It does not describe return values or error behavior, and there is no output schema, so this is a minor gap for a 12-parameter mutating tool. Overall it is substantially complete.

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 100%, so the baseline is 3. The description adds meaning beyond the schema: the patch-like behavior of 'only the fields you provide change' and the combined DHCP-disable rule that passing both empty dhcp_start and dhcp_stop disables DHCP. The per-argument list largely restates the schema, which prevents a 5.

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?

States a specific verb and resource: 'Update a network/VLAN,' and clarifies the patch semantics with 'only the fields you provide change.' It also distinguishes the read counterpart by saying 'Inspect with get_networks,' and the update operation is clearly separate from sibling creation/deletion tools like create_network and delete_network.

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?

Provides clear context on when this tool is appropriate: updating an existing network, with immediate persistence, and requiring confirm=true. It also names get_networks as the inspection alternative. It does not explicitly state exclusions such as 'use create_network to add a network' or 'use delete_network to remove one,' but the update semantics make those distinctions inferable.

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