interface_health_rca

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

readOnlyHint=true already covers the safety profile, but the description adds real behavioral detail: it names the two upstream calls it makes, describes the output ordering (worst-first), and states each finding cites the measured number with a cause and concrete action. That is meaningful disclosure about what the tool does and returns 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?

Front-loaded with the [READ] tag and a one-line purpose, then the mechanism, then the single arg. Every sentence earns its place with no filler.

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?

With no output schema, the description steps in by describing the report shape (worst-first findings, cited measurements, cause, action), so an agent knows what to expect. Still no mention of pagination or scoping limits, but for a single-param read diagnostic it 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?

Schema coverage is 0%, so the description must carry the parameter. It does: 'target: Device name from config; omit to use the default device' explains both the value source and the optional-default behavior, which the bare anyOf[string, null] schema does not convey.

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 verb 'Flag' and the resource 'interfaces' are specific, and the qualifying conditions (admin-up/oper-down, erroring, discarding, flapping) pin down exactly what it detects. It is clearly distinguishable from the sibling get_interfaces and get_interfaces_counters that it consumes as inputs.

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?

By stating it 'pulls get_interfaces + get_interfaces_counters,' it implicitly positions itself as the diagnostic layer above those raw readers. However, it never explicitly says 'use this instead of get_interfaces_counters when you want interpreted findings,' so the when/when-not routing is left to inference.

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