update_network_vlan

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the write/destructive nature is covered structurally. The description adds genuinely new context: it captures changed keys' prior values and that undo restores them (consistent with the sibling undo_list/undo_apply), plus the dry_run preview path. It stops short of describing failure behavior or response shape, but adds real value beyond the 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?

Front-loads the write/risk tag and the key behavioral fact (prior-value capture + undo), then a clean Args list. Every line is relevant. Minor redundancy between the top-line 'capturing its prior values' and the parenthetical 'undo restores them,' but overall tight.

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 5-param mutation with no output schema, the description covers purpose, reversibility, preview, and per-parameter meaning. The only gap is the return value on success/failure, which is not addressed, but with no output schema and strong parameter coverage the definition is largely 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?

With 0% schema description coverage and a nested free-form attrs object, the description carries the full burden and does: it names all five parameters and critically enumerates the allowed attrs keys (name, subnet, applianceIp, groupPolicyId, dhcpHandling), which the schema does not. This is exactly the compensation needed for an under-documented nested object.

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 an appliance VLAN') and adds a scope/tag marker ([WRITE][risk=medium]) that instantly separates it from read siblings like network_vlans or overview. An agent can identify the operation and its mutation nature without opening the schema.

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 actionable invocation guidance — pass dry_run=True to preview, and omit target to use the default — but never states when to choose this over alternatives or any preconditions/exclusions. Usage is implied through the preview hint rather than explicitly framed as when/when-not.

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