gateway_health_rca

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

Annotations are none, so the description carries the full burden. It discloses that this is a READ operation via the '[READ]' prefix, that it pulls live status data when a target is given, and that it can skip the live pull via the 'gateways' arg. It also reveals the return structure and that ranking includes numbers ('not a black-box verdict'), giving good behavioral context.

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 well-organized with a clear opening line, an intro paragraph, and a structured Args section with defaults. The only slight waste is the redundant '[READ]' tag alongside the intro paragraph re-stating it pulls status. Overall tight and front-loaded.

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 no annotations and no output schema, the description handles the core needs well: it states the read-only nature, explains inputs, describes the full return dict shape, and gives default thresholds. Minor gaps remain (conflict handling between gateways and target, exact criteria for 'degraded'), but it is reasonably complete for an RCA tool.

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%, so the description must compensate. It does explain each parameter (loss_pct and latency_ms thresholds with defaults, gateways as injected rows that skip live pull, target as firewall name from config). However, the gateways parameter is described but its exact schema relationship is thin, and there's no note about what happens if both gateways and target are provided together. Compensates partially but not fully given zero coverage.

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 is specific and clear: 'Rank gateways by loss + latency, map each down/degraded one to cause + action.' It identifies the resource (gateways), the verb (rank/map), and the exact output structure. Despite siblings like gateway_status and health_status, it clearly distinguishes itself as the analytics/RCA tool that produces rankings with causes and actions, not just raw status.

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 gives clear context for when to use it ('The flagship WAN RCA'), notes it 'pulls gateway status' and flags down/degraded gateways, and explains the two modes: pass 'gateways' for pure analysis or a target for live pull. It doesn't explicitly name sibling alternatives to exclude, but the use cases are clearly framed around RCA/ranking vs. the simpler status tools.

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