Patch firewall policy

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuine context by stating PATCH semantics, meaning unspecified fields are preserved rather than reset. However it omits the critical fact that without confirm="YES" the call is only a preview — that behavior is discoverable only from the schema.

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?

A single well-formed sentence with the key distinction front-loaded. The '(PATCH semantics)' parenthetical is mildly redundant with 'partially updates' but still helps an agent reason about partial payloads.

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?

This is a destructive mutation with no output schema and only 50% schema coverage, yet the description omits the two-stage preview/apply behavior (confirm="YES" required to actually write) and says nothing about what a patch returns. As written, an agent could believe a bare call applies changes when it only produces a preview.

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 50% and the two most important parameters (id, body) have no schema descriptions at all. 'Partially updates' weakly implies body need only contain changed fields, but the description never explains the id, what body accepts, or the interaction between confirm and dry_run.

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 phrase ('partially updates') and resource ('existing firewall policy'), and the PATCH parenthetical implies the difference from a full update. It does not name the sibling tool unifi_net_update_firewall_policy explicitly, but the partial-vs-full distinction is clear enough to separate them.

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 'partially' implies when this tool is appropriate (only some fields change), but there is no explicit when-to-use or when-not guidance versus unifi_net_update_firewall_policy, and no mention of the confirmation/preview workflow that governs whether anything is actually applied.

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