hcl_apply_vlan

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the bar is lower, yet the description still adds real value: it discloses the backup/readback/recovery lifecycle and the non-obvious semantics that native trunk membership is REPLACED with the exact allowed VLAN set, which an agent would otherwise not know. It does not explain what backup/readback produce or what 'recovery' triggers, but the core destructive semantic is surfaced.

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?

Two short sentences, front-loaded with purpose and followed by the one non-obvious behavioral rule. No filler, though the trailing newline and slightly telegraphic style leave room for a tighter single statement.

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 destructive, non-idempotent write tool with a nested schema, no output schema and no parameter docs, the description covers the safety posture and trunk replacement but omits prerequisites (project/topology/device resolution), what backup/readback/recovery concretely do, and the effect of dry_run. Minimum viable but with clear gaps.

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 0% across five parameters with deeply nested objects (vlans, names, ports, svis, native_vlan, allowed_vlans), so the description must carry the load. It only clarifies one semantic (native trunk membership is replaced by allowed_vlans); it says nothing about dry_run behavior, topology/project_path/device expectations, or how ports/svis/names interact. Large gap for a 0%-coverage schema.

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 (apply) and resource (VLAN/port/SVI intent) and scopes it to a single device, which separates it from the network-wide sibling hcl_apply_vlan_network. It also names the safety rails (backup, readback, recovery) so the agent knows this is a staged, reversible-ish operation rather than a raw push.

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 word 'strict' and 'single-device' imply this is the per-device enforcement path versus the network-wide apply, but usage is only implied. There is no explicit when-to-use/when-not, no mention of preconditions (project must be open, topology/device must exist), and no pointer to hcl_apply_vlan_network or hcl_validate_plan as the alternative.

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